2019
Raluca D. Gaina, Simon M. Lucas, Diego Perez-Liebana,
"Tackling Sparse Rewards in Real-Time Games with Statistical Forward Planning Methods",
in AAAI Conference on Artificial Intelligence (AAAI-19),
2019.
Abstract
One of the issues general AI game players are required to deal with is the different reward systems in the variety of games they are expected to be able to play at a high level. Some games may present plentiful rewards which the agents can use to guide their search for the best solution, whereas others feature sparse reward landscapes that provide little information to the agents. The work presented in this paper focuses on the latter case, which most agents struggle with. Thus, modifications are proposed for two algorithms, Monte Carlo Tree Search and Rolling Horizon Evolutionary Algorithms, aiming at improving performance in this type of games while maintaining overall win rate across those where rewards are plentiful. Results show that longer rollouts and individual lengths, either fixed or responsive to changes in fitness landscape features, lead to a boost of performance in the games during testing without being detrimental to non-sparse reward scenarios.
Note
BibTex
@inproceedings{gaina2019sparse-rewards,
author: {Raluca D. Gaina and Simon M. Lucas and Diego Perez-Liebana},
title: {{Tackling Sparse Rewards in Real-Time Games with Statistical Forward Planning Methods}},
year: {2019},
booktitle: {{AAAI Conference on Artificial Intelligence (AAAI-19)}},
abstract: {One of the issues general AI game players are required to deal with is the different reward systems in the variety of games they are expected to be able to play at a high level. Some games may present plentiful rewards which the agents can use to guide their search for the best solution, whereas others feature sparse reward landscapes that provide little information to the agents. The work presented in this paper focuses on the latter case, which most agents struggle with. Thus, modifications are proposed for two algorithms, Monte Carlo Tree Search and Rolling Horizon Evolutionary Algorithms, aiming at improving performance in this type of games while maintaining overall win rate across those where rewards are plentiful. Results show that longer rollouts and individual lengths, either fixed or responsive to changes in fitness landscape features, lead to a boost of performance in the games during testing without being detrimental to non-sparse reward scenarios.},
}
Diego Perez-Liebana, Jialin Liu, Ahmed Khalifa, Raluca D. Gaina, Julian Togelius, Simon M. Lucas,
"General Video Game AI: a Multi-Track Framework for Evaluating Agents Games and Content Generation Algorithms",
in IEEE Transactions on Games,
abs/1802.10363,
pp. 1-1,
2019.
Abstract
General Video Game Playing (GVGP) aims at designing an agent that is capable of playing multiple video games with no human intervention. In 2014, The General Video Game AI (GVGAI) competition framework was created and released with the purpose of providing researchers a common open-source and easy to use platform for testing their AI methods with potentially infinity of games created using Video Game Description Language (VGDL). The framework has been expanded into several tracks during the last few years to meet the demand of different research directions. The agents are required either to play multiple unknown games with or without access to game simulations, or to design new game levels or rules. This survey paper presents the VGDL, the GVGAI framework, existing tracks, and reviews the wide use of GVGAI framework in research, education and competitions five years after its birth. A future plan of framework improvements is also described.
Note
BibTex
@article{perez2018gvgaisurvey,
author: {Diego Perez-Liebana and Jialin Liu and Ahmed Khalifa and Raluca D. Gaina and Julian Togelius and Simon M. Lucas},
title: {{General Video Game AI: a Multi-Track Framework for Evaluating Agents Games and Content Generation Algorithms}},
year: {2019},
journal: {{IEEE Transactions on Games}},
volume: {abs/1802.10363},
pages: {1-1},
keywords: {Games;Sprites (computer);Artificial intelligence;Planning;Benchmark testing;Education;Computational intelligence;artificial intelligence;games;general video game playing;GVGAI;video game description language},
url: {https://ieeexplore.ieee.org/abstract/document/8664126},
doi: {10.1109/TG.2019.2901021},
abstract: {General Video Game Playing (GVGP) aims at designing an agent that is capable of playing multiple video games with no human intervention. In 2014, The General Video Game AI (GVGAI) competition framework was created and released with the purpose of providing researchers a common open-source and easy to use platform for testing their AI methods with potentially infinity of games created using Video Game Description Language (VGDL). The framework has been expanded into several tracks during the last few years to meet the demand of different research directions. The agents are required either to play multiple unknown games with or without access to game simulations, or to design new game levels or rules. This survey paper presents the VGDL, the GVGAI framework, existing tracks, and reviews the wide use of GVGAI framework in research, education and competitions five years after its birth. A future plan of framework improvements is also described.},
}
Raluca D. Gaina, Simon M. Lucas, Diego Perez-Liebana,
"Project Thyia: A Forever Gameplayer",
in accepted at IEEE Conference on Games (COG),
2019.
Abstract
The space of Artificial Intelligence entities is dominated by conversational bots. Some of them fit in our pockets and we take them everywhere we go, or allow them to be a part of human homes. Siri, Alexa, they are recognised as present in our world. But a lot of games research is restricted to existing in the separate realm of software. We enter different worlds when playing games, but those worlds cease to exist once we quit. Similarly, AI game-players are run once on a game (or maybe for longer periods of time, in the case of learning algorithms which need some, still limited, period for training), and they cease to exist once the game ends. But what if they didn’t? What if there existed artificial game-players that continuously played games, learned from their experiences and kept getting better? What if they interacted with the real world and us, humans: livestreaming games, chatting with viewers, accepting suggestions for strategies or games to play, forming opinions on popular game titles? In this paper, we introduce the vision behind a new project called Thyia, which focuses around creating a present, continuous, ‘always-on’, interactive game-player.
Note
BibTex
@inproceedings{gaina2019thyia,
author: {Raluca D. Gaina and Simon M. Lucas and Diego Perez-Liebana},
title: {{Project Thyia: A Forever Gameplayer}},
year: {2019},
booktitle: {{accepted at IEEE Conference on Games (COG)}},
eprint: {http://arxiv.org/abs/1906.04023},
abstract: {The space of Artificial Intelligence entities is dominated by conversational bots. Some of them fit in our pockets and we take them everywhere we go, or allow them to be a part of human homes. Siri, Alexa, they are recognised as present in our world. But a lot of games research is restricted to existing in the separate realm of software. We enter different worlds when playing games, but those worlds cease to exist once we quit. Similarly, AI game-players are run once on a game (or maybe for longer periods of time, in the case of learning algorithms which need some, still limited, period for training), and they cease to exist once the game ends. But what if they didn’t? What if there existed artificial game-players that continuously played games, learned from their experiences and kept getting better? What if they interacted with the real world and us, humans: livestreaming games, chatting with viewers, accepting suggestions for strategies or games to play, forming opinions on popular game titles? In this paper, we introduce the vision behind a new project called Thyia, which focuses around creating a present, continuous, ‘always-on’, interactive game-player.},
}
Raluca D. Gaina, Matthew Stephenson,
"'Did You Hear That?' Learning to Play Video Games from Audio Cues",
in accepted at IEEE Conference on Games (COG),
2019.
Abstract
Game-playing AI research has focused for a long time on learning to play video games from visual input or symbolic information. However, humans benefit from a wider array of sensors which we utilise in order to navigate the world around us. In particular, sounds and music are key to how many of us perceive the world and influence the decisions we make. In this paper, we present initial experiments on game-playing agents learning to play video games solely from audio cues. We expand the Video Game Description Language to allow for audio specification, and the General Video Game AI framework to provide new audio games and an API for learning agents to make use of audio observations. We analyse the games and the audio game design process, include initial results with simple Q-Learning agents, and encourage further research in this area.
Note
BibTex
@inproceedings{gaina2019audio,
author: {Raluca D. Gaina and Matthew Stephenson},
title: {{'Did You Hear That?' Learning to Play Video Games from Audio Cues}},
year: {2019},
booktitle: {{accepted at IEEE Conference on Games (COG)}},
eprint: {http://arxiv.org/abs/1906.04027},
abstract: {Game-playing AI research has focused for a long time on learning to play video games from visual input or symbolic information. However, humans benefit from a wider array of sensors which we utilise in order to navigate the world around us. In particular, sounds and music are key to how many of us perceive the world and influence the decisions we make. In this paper, we present initial experiments on game-playing agents learning to play video games solely from audio cues. We expand the Video Game Description Language to allow for audio specification, and the General Video Game AI framework to provide new audio games and an API for learning agents to make use of audio observations. We analyse the games and the audio game design process, include initial results with simple Q-Learning agents, and encourage further research in this area.},
}
Olve Drageset, Raluca D. Gaina, Diego Perez-Liebana, Mark H.M. Winands,
"Optimising Level Generators for General Video Game AI",
in accepted at IEEE Conference on Games (COG),
2019.
Abstract
Procedural Content Generation is an active area of research, with more interest being given recently to methods able to produce interesting content in a general context (without task-specific knowledge). To this extent, we focus on procedural level generators within the General Video Game AI framework (GVGAI). This paper proposes several topics of interest. First, a comparison baseline for GVGAI level generators, which is more flexible and robust than the existing alternatives. Second, a composite fitness evaluation function for levels based on AI play-testing. Third, a new parameterized generator, and a Meta Generator for performing parameter search on such generators are introduced. We compare the Meta Generator against random and constructive generator baselines, using the new fitness function, on 3 GVGAI games: Butterflies, Freeway and The Snowman. The Meta Generator is suggested to perform on par with or better than the baselines, depending on the game. Encouraged by these results, the Meta Generator will be submitted to the 2019 GVGAI Level Generation competition.
Note
BibTex
@inproceedings{drageset2019generator,
author: {Olve Drageset and Raluca D. Gaina and Diego Perez-Liebana and Mark H.M. Winands},
title: {{Optimising Level Generators for General Video Game AI}},
year: {2019},
booktitle: {{accepted at IEEE Conference on Games (COG)}},
abstract: {Procedural Content Generation is an active area of research, with more interest being given recently to methods able to produce interesting content in a general context (without task-specific knowledge). To this extent, we focus on procedural level generators within the General Video Game AI framework (GVGAI). This paper proposes several topics of interest. First, a comparison baseline for GVGAI level generators, which is more flexible and robust than the existing alternatives. Second, a composite fitness evaluation function for levels based on AI play-testing. Third, a new parameterized generator, and a Meta Generator for performing parameter search on such generators are introduced. We compare the Meta Generator against random and constructive generator baselines, using the new fitness function, on 3 GVGAI games: Butterflies, Freeway and The Snowman. The Meta Generator is suggested to perform on par with or better than the baselines, depending on the game. Encouraged by these results, the Meta Generator will be submitted to the 2019 GVGAI Level Generation competition.},
}
Alexander Dockhorn, Simon M Lucas, Vanessa Volz, Ivan Bravi, Raluca D. Gaina, Diego Perez-Liebana,
"Learning Local Forward Models on Unforgiving Games",
in accepted at IEEE Conference on Games (COG),
2019.
Abstract
This paper examines learning approaches for forward models based on local cell transition function. We provide a formal definition of local forward models for which we propose two learning approaches. Our analysis is based on the game Sokoban, where a wrong action can lead to an unsolvable game state. Therefore, an accurate prediction of an action's resulting state is necessary to avoid this scenario. In contrast to learning the complete state transition function, local forward models allow extracting multiple training examples from a single state transition. In this way, the Hash Set model, as well as the Decision Tree model, quickly learn to predict upcoming state transitions of both the training and the test set. Applying the model using a statistical forward planner showed that the best models can be used to satisfying degree even in cases in which the test levels have not yet been seen. Our evaluation includes an analysis of various local neighbourhood patterns and sizes to test the learners' capabilities in case too few or too many attributes are extracted, of which the latter has shown do degrade the performance of the model learner.
Note
BibTex
@inproceedings{dockhorn2019unforgiving,
author: {Alexander Dockhorn and Simon M Lucas and Vanessa Volz and Ivan Bravi and Raluca D. Gaina and Diego Perez-Liebana},
title: {{Learning Local Forward Models on Unforgiving Games}},
year: {2019},
booktitle: {{accepted at IEEE Conference on Games (COG)}},
abstract: {This paper examines learning approaches for forward models based on local cell transition function. We provide a formal definition of local forward models for which we propose two learning approaches. Our analysis is based on the game Sokoban, where a wrong action can lead to an unsolvable game state. Therefore, an accurate prediction of an action's resulting state is necessary to avoid this scenario. In contrast to learning the complete state transition function, local forward models allow extracting multiple training examples from a single state transition. In this way, the Hash Set model, as well as the Decision Tree model, quickly learn to predict upcoming state transitions of both the training and the test set. Applying the model using a statistical forward planner showed that the best models can be used to satisfying degree even in cases in which the test levels have not yet been seen. Our evaluation includes an analysis of various local neighbourhood patterns and sizes to test the learners' capabilities in case too few or too many attributes are extracted, of which the latter has shown do degrade the performance of the model learner.},
}
Simon M Lucas, Alexander Dockhorn, Vanessa Volz, Chris Bamford, Raluca D. Gaina, Ivan Bravi, Diego Perez-Liebana, Sanaz Mostaghim, Rudolf Kruse,
"A Local Approach to Forward Model Learning: Results on the Game of Life Game",
in accepted at IEEE Conference on Games (COG),
2019.
Abstract
This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a single-player game where the objective can be either to preserve as much life as possible or to extinguish all life as quickly as possible. In order to learn the forward model of the game, we formulate the problem in a novel way that learns the local cell transition function by creating a set of supervised training data and predicting the next state of each cell in the grid based on its current state and immediate neighbours. Using this method we are able to harvest sufficient data to learn perfect forward models by observing only a few complete state transitions, using either a look-up table, a decision tree, or a neural network. In contrast, learning the complete state transition function is a much harder task and our initial efforts to do this using deep convolutional auto-encoders were less successful. We also investigate the effects of imperfect learned models on prediction errors and game-playing performance, and show that even models with significant errors can provide good performance.
Note
BibTex
@inproceedings{lucas2019gog,
author: {Simon M Lucas and Alexander Dockhorn and Vanessa Volz and Chris Bamford and Raluca D. Gaina and Ivan Bravi and Diego Perez-Liebana and Sanaz Mostaghim and Rudolf Kruse},
title: {{A Local Approach to Forward Model Learning: Results on the Game of Life Game}},
year: {2019},
booktitle: {{accepted at IEEE Conference on Games (COG)}},
eprint: {https://arxiv.org/abs/1903.12508},
abstract: {This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a single-player game where the objective can be either to preserve as much life as possible or to extinguish all life as quickly as possible. In order to learn the forward model of the game, we formulate the problem in a novel way that learns the local cell transition function by creating a set of supervised training data and predicting the next state of each cell in the grid based on its current state and immediate neighbours. Using this method we are able to harvest sufficient data to learn perfect forward models by observing only a few complete state transitions, using either a look-up table, a decision tree, or a neural network. In contrast, learning the complete state transition function is a much harder task and our initial efforts to do this using deep convolutional auto-encoders were less successful. We also investigate the effects of imperfect learned models on prediction errors and game-playing performance, and show that even models with significant errors can provide good performance.},
}
Simon M Lucas, Jialin Liu, Ivan Bravi, Raluca D. Gaina, John Woodward, Vanessa Volz, Diego Perez-Liebana,
"Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best",
in Game Simulations Workshop (AAAI),
2019.
Abstract
This paper introduces a simple and fast variant of Planet Wars as a test-bed for statistical planning based Game AI agents, and for noisy hyper-parameter optimisation. Planet Wars is a real-time strategy game with simple rules but complex game-play. The variant introduced in this paper is designed for speed to enable efficient experimentation, and also for a fixed action space to enable practical inter-operability with General Video Game AI agents. If we treat the game as a win-loss game (which is standard), then this leads to challenging noisy optimisation problems both in tuning agents to play the game, and in tuning game parameters. Here we focus on the problem of tuning an agent, and report results using the recently developed N-Tuple Bandit Evolutionary Algorithm and a number of other optimisers, including Sequential Model-based Algorithm Configuration (SMAC). Results indicate that the N-Tuple Bandit Evolutionary Algorithm offers competitive performance as well as insight into the effects of combinations of parameter choices.
Note
BibTex
@inproceedings{lucas2019efficient,
author: {Simon M Lucas and Jialin Liu and Ivan Bravi and Raluca D. Gaina and John Woodward and Vanessa Volz and Diego Perez-Liebana},
title: {{Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best}},
year: {2019},
booktitle: {{Game Simulations Workshop (AAAI)}},
eprint: {https://arxiv.org/abs/1901.00723},
abstract: {This paper introduces a simple and fast variant of Planet Wars as a test-bed for statistical planning based Game AI agents, and for noisy hyper-parameter optimisation. Planet Wars is a real-time strategy game with simple rules but complex game-play. The variant introduced in this paper is designed for speed to enable efficient experimentation, and also for a fixed action space to enable practical inter-operability with General Video Game AI agents. If we treat the game as a win-loss game (which is standard), then this leads to challenging noisy optimisation problems both in tuning agents to play the game, and in tuning game parameters. Here we focus on the problem of tuning an agent, and report results using the recently developed N-Tuple Bandit Evolutionary Algorithm and a number of other optimisers, including Sequential Model-based Algorithm Configuration (SMAC). Results indicate that the N-Tuple Bandit Evolutionary Algorithm offers competitive performance as well as insight into the effects of combinations of parameter choices.},
}
2018
Gaina, Raluca D., Couetoux, Adrien, Soemers, Dennis J.N.J., Winands, Mark H.M., Vodopivec, Tom, Kirchgessner, Florian, Liu, Jialin, Lucas, Simon M., Perez-Liebana, Diego,
"The 2016 Two-Player GVGAI Competition",
in IEEE Transactions on Games,
10,
pp. 209-220,
June, 2018.
Abstract
This paper showcases the setting and results of the first Two-Player General Video Game AI competition, which ran in 2016 at the IEEE World Congress on Computational Intelligence and the IEEE Conference on Computational Intelligence and Games. The challenges for the general game AI agents are expanded in this track from the single-player version, looking at direct player interaction in both competitive and cooperative environments of various types and degrees of difficulty. The focus is on the agents not only handling multiple problems, but also having to account for another intelligent entity in the game, who is expected to work towards their own goals (winning the game). This other player will possibly interact with first agent in a more engaging way than the environment or any non-playing character may do. The top competition entries are analyzed in detail and the performance of all agents is compared across the four sets of games. The results validate the competition system in assessing generality, as well as showing Monte Carlo Tree Search continuing to dominate by winning the overall Championship. However, this approach is closely followed by Rolling Horizon Evolutionary Algorithms, employed by the winner of the second leg of the contest.
Note
BibTex
@article{gaina2018gvgai2P,
author: {Gaina, Raluca D. and Couetoux, Adrien and Soemers, Dennis J.N.J. and Winands, Mark H.M. and Vodopivec, Tom and Kirchgessner, Florian and Liu, Jialin and Lucas, Simon M. and Perez-Liebana, Diego},
title: {{The 2016 Two-Player GVGAI Competition}},
year: {2018},
journal: {{IEEE Transactions on Games}},
month: {June},
volume: {10},
number: {2},
pages: {209--220},
keywords: {artificial intelligence;computer games;evolutionary computation;Monte Carlo methods;tree searching;Two-Player GVGAI Competition;Two-Player General Video Game AI Competition;IEEE World Congress;Computational Intelligence;IEEE Conference;general game AI agents;single-player version;direct player interaction;competitive environments;cooperative environments;competition entries;competition system;Games;Artificial intelligence;Real-time systems;Electronic mail;Monte Carlo methods;Computer science;Evolutionary computation;Competitions;general video game playing (GVGP);Monte Carlo tree search (MCTS);multiplayer games;real-time games;rolling horizon evolutionary algorithms (RHEAs)},
url: {http://ieeexplore.ieee.org/document/8100955/},
doi: {10.1109/TCIAIG.2017.2771241},
abstract: {This paper showcases the setting and results of the first Two-Player General Video Game AI competition, which ran in 2016 at the IEEE World Congress on Computational Intelligence and the IEEE Conference on Computational Intelligence and Games. The challenges for the general game AI agents are expanded in this track from the single-player version, looking at direct player interaction in both competitive and cooperative environments of various types and degrees of difficulty. The focus is on the agents not only handling multiple problems, but also having to account for another intelligent entity in the game, who is expected to work towards their own goals (winning the game). This other player will possibly interact with first agent in a more engaging way than the environment or any non-playing character may do. The top competition entries are analyzed in detail and the performance of all agents is compared across the four sets of games. The results validate the competition system in assessing generality, as well as showing Monte Carlo Tree Search continuing to dominate by winning the overall Championship. However, this approach is closely followed by Rolling Horizon Evolutionary Algorithms, employed by the winner of the second leg of the contest.},
}
Raluca D. Gaina, Simon M. Lucas, Diego Perez-Liebana,
"VERTIGO: Visualisation of Rolling Horizon Evolutionary Algorithms in GVGAI",
in The 14th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment,
pp. 265-267,
2018.
Abstract
This report presents a tool developed for the analysis and visualisation of Rolling Horizon Evolutionary Algorithms, featuring a GUI which allows integration within the General Video Game AI Framework. Users are able to easily customize the parameters of the agent between runs and observe an in-depth analysis of its performance through various visual information extracted from gameplay data, live while playing the game. This visualisation aims to inform a deeper analysis into algorithm behaviour, in an attempt to justify why they make the decisions they do and improve their performance based on this knowledge.
Note
BibTex
@inproceedings{gaina2018vertigo,
author: {Raluca D. Gaina and Simon M. Lucas and Diego Perez-Liebana},
title: {{VERTIGO: Visualisation of Rolling Horizon Evolutionary Algorithms in GVGAI}},
year: {2018},
booktitle: {{The 14th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment}},
pages: {265--267},
url: {https://aaai.org/ocs/index.php/AIIDE/AIIDE18/paper/view/18100},
abstract: {This report presents a tool developed for the analysis and visualisation of Rolling Horizon Evolutionary Algorithms, featuring a GUI which allows integration within the General Video Game AI Framework. Users are able to easily customize the parameters of the agent between runs and observe an in-depth analysis of its performance through various visual information extracted from gameplay data, live while playing the game. This visualisation aims to inform a deeper analysis into algorithm behaviour, in an attempt to justify why they make the decisions they do and improve their performance based on this knowledge.},
}
Raluca D. Gaina, Simon M. Lucas, Diego Perez-Liebana,
"General Win Prediction from Agent Experience",
in Proc. of the IEEE Conference on Computational Intelligence and Games (CIG),
pp. 1-8,
Aug, 2018.
Abstract
The question of whether the correct algorithm is used for the problem at hand usually comes at the end of execution, when the algorithm's ability to solve the problem (or not) can be verified. But what if this question could be answered in advance, with enough notice to make changes in the approach in order for it to be more successful? This paper proposes a general agent performance prediction system, tested in real time within the context of the General Video Game AI framework. It is solely based on agent features, therefore removing potential human bias produced by game-based features observed in known games. Three different models can be queried while playing the game to determine whether the agent will win or lose, based on the current game state: early, mid and late game feature models. The models are trained on 80 games in the framework and tested on 20 new games, for 14 variations of 3 different methods. Results are positive, indicating that there is great scope for predicting the outcome of any given game.
Note
BibTex
@inproceedings{gaina2018win,
author: {Raluca D. Gaina and Simon M. Lucas and Diego Perez-Liebana},
title: {{General Win Prediction from Agent Experience}},
year: {2018},
booktitle: {{Proc. of the IEEE Conference on Computational Intelligence and Games (CIG)}},
month: {Aug},
pages: {1--8},
keywords: {artificial intelligence;computer games;game theory;agent experience;game-based features;prediction system;video game AI framework;Games;Artificial intelligence;Feature extraction;Monte Carlo methods;Measurement;Sociology;general video game playing;rolling horizon evolution;monte carlo tree search;win prediction},
url: {https://ieeexplore.ieee.org/document/8490439},
doi: {10.1109/CIG.2018.8490439},
abstract: {The question of whether the correct algorithm is used for the problem at hand usually comes at the end of execution, when the algorithm's ability to solve the problem (or not) can be verified. But what if this question could be answered in advance, with enough notice to make changes in the approach in order for it to be more successful? This paper proposes a general agent performance prediction system, tested in real time within the context of the General Video Game AI framework. It is solely based on agent features, therefore removing potential human bias produced by game-based features observed in known games. Three different models can be queried while playing the game to determine whether the agent will win or lose, based on the current game state: early, mid and late game feature models. The models are trained on 80 games in the framework and tested on 20 new games, for 14 variations of 3 different methods. Results are positive, indicating that there is great scope for predicting the outcome of any given game.},
}
Chiara F. Sironi, Jialin Liu, Diego Perez-Liebana, Raluca D. Gaina, Ivan Bravi, Simon M. Lucas, Mark H. M. Winands,
"Self-adaptive MCTS for General Video Game Playing",
in Applications of Evolutionary Computation,
pp. 358-375,
2018.
Abstract
Monte-Carlo Tree Search (MCTS) has shown particular success in General Game Playing (GGP) and General Video Game Playing (GVGP) and many enhancements and variants have been developed. Recently, an on-line adaptive parameter tuning mechanism for MCTS agents has been proposed that almost achieves the same performance as off-line tuning in GGP. In this paper we apply the same approach to GVGP and use the popular General Video Game AI (GVGAI) framework, in which the time allowed to make a decision is only 40ms. We design three Self-Adaptive MCTS (SA-MCTS) agents that optimize on-line the parameters of a standard non-Self-Adaptive MCTS agent of GVGAI. The three agents select the parameter values using Naïve Monte-Carlo, an Evolutionary Algorithm and an N-Tuple Bandit Evolutionary Algorithm respectively, and are tested on 20 single-player games of GVGAI. The SA-MCTS agents achieve more robust results on the tested games. With the same time setting, they perform similarly to the baseline standard MCTS agent in the games for which the baseline agent performs well, and significantly improve the win rate in the games for which the baseline agent performs poorly. As validation, we also test the performance of non-Self-Adaptive MCTS instances that use the most sampled parameter settings during the on-line tuning of each of the three SA-MCTS agents for each game. Results show that these parameter settings improve the win rate on the games Wait for Breakfast and Escape by 4 times and 150 times, respectively.
Note
978-3-319-77538-8
BibTex
@inproceedings{sironi2018mctsGVGP,
author: {Chiara F. Sironi and Jialin Liu and Diego Perez-Liebana and Raluca D. Gaina and Ivan Bravi and Simon M. Lucas and Mark H. M. Winands},
title: {{Self-adaptive MCTS for General Video Game Playing}},
year: {2018},
booktitle: {{Applications of Evolutionary Computation}},
pages: {358--375},
editor: {Kevin Sim and Paul Kaufmann},
publisher: {Springer International Publishing},
address: {Cham},
url: {https://link.springer.com/chapter/10.1007/978-3-319-77538-8_25},
isbn: {978-3-319-77538-8},
abstract: {Monte-Carlo Tree Search (MCTS) has shown particular success in General Game Playing (GGP) and General Video Game Playing (GVGP) and many enhancements and variants have been developed. Recently, an on-line adaptive parameter tuning mechanism for MCTS agents has been proposed that almost achieves the same performance as off-line tuning in GGP. In this paper we apply the same approach to GVGP and use the popular General Video Game AI (GVGAI) framework, in which the time allowed to make a decision is only 40ms. We design three Self-Adaptive MCTS (SA-MCTS) agents that optimize on-line the parameters of a standard non-Self-Adaptive MCTS agent of GVGAI. The three agents select the parameter values using Naïve Monte-Carlo, an Evolutionary Algorithm and an N-Tuple Bandit Evolutionary Algorithm respectively, and are tested on 20 single-player games of GVGAI. The SA-MCTS agents achieve more robust results on the tested games. With the same time setting, they perform similarly to the baseline standard MCTS agent in the games for which the baseline agent performs well, and significantly improve the win rate in the games for which the baseline agent performs poorly. As validation, we also test the performance of non-Self-Adaptive MCTS instances that use the most sampled parameter settings during the on-line tuning of each of the three SA-MCTS agents for each game. Results show that these parameter settings improve the win rate on the games Wait for Breakfast and Escape by 4 times and 150 times, respectively.},
}
Kunanusont, Kamolwan, Lucas, Simon M, Perez-Liebana, Diego,
"Modelling Player Experience with the N-Tuple Bandit Evolutionary Algorithm",
in Artificial intelligence and Interactive Digital Entertainment (AIIDE),
2018.
Abstract
Note
BibTex
@inproceedings{kunanusont2018scoretrend,
author: {Kunanusont, Kamolwan and Lucas, Simon M and Perez-Liebana, Diego},
title: {{Modelling Player Experience with the N-Tuple Bandit Evolutionary Algorithm}},
year: {2018},
booktitle: {{Artificial intelligence and Interactive Digital Entertainment (AIIDE)}},
}
Lucas, Simon M., Liu, Jialin, Perez-Liebana, Diego,
"The N-Tuple Bandit Evolutionary Algorithm for Game Agent Optimisation",
in arXiv preprint arXiv:1802.05991,
2018.
Abstract
Note
BibTex
@article{lucas2018ntuple,
author: {Lucas, Simon M. and Liu, Jialin and Perez-Liebana, Diego},
title: {{The N-Tuple Bandit Evolutionary Algorithm for Game Agent Optimisation}},
year: {2018},
journal: {{arXiv preprint arXiv:1802.05991}},
}
Bravi, Ivan, Perez-Liebana, Diego, Lucas, Simon M, Liu, Jialin,
"Shallow Decision-making Analysis in General Video Game Playing",
2018.
Abstract
Note
BibTex
@inproceedings{Bravi2018,
author: {Bravi, Ivan and Perez-Liebana, Diego and Lucas, Simon M and Liu, Jialin},
title: {{Shallow Decision-making Analysis in General Video Game Playing}},
year: {2018},
}
Ashlock, Daniel, Kim, Eun-Youn M, Perez-Liebana, Diego,
"Toward General Mathematical Game Playing Agents",
2018.
Abstract
Note
BibTex
@inproceedings{Ashlock2018,
author: {Ashlock, Daniel and Kim, Eun-Youn M and Perez-Liebana, Diego},
title: {{Toward General Mathematical Game Playing Agents}},
year: {2018},
}
Torrado, Ruben R., Bontrager, Philip, Togelius, Julian, Liu, Jialin, Perez-Liebana, Diego,
"Deep Reinforcement Learning in the General Video Game AI framework",
2018.
Abstract
Note
BibTex
@inproceedings{Torrado2018,
author: {Torrado, Ruben R. and Bontrager, Philip and Togelius, Julian and Liu, Jialin and Perez-Liebana, Diego},
title: {{Deep Reinforcement Learning in the General Video Game AI framework}},
year: {2018},
}
Guerrero-Romero, Cristina, Lucas, Simon M, Perez-Liebana, Diego,
"Using a Team of General AI Algorithms to Assist Game Design and Testing",
2018.
Abstract
Note
BibTex
@inproceedings{Guerrero2018,
author: {Guerrero-Romero, Cristina and Lucas, Simon M and Perez-Liebana, Diego},
title: {{Using a Team of General AI Algorithms to Assist Game Design and Testing}},
year: {2018},
}
Perez-Liebana, Diego, Hofmann, Katja, Mohanty, Sharada Prasanna, Kuno, Noburu, Kramer, Andre, Devlin, Sam, Gaina, Raluca D, Ionita, Daniel,
"The Multi-Agent Reinforcement Learning in MalmO (MARLO) Competition",
in Challenges in Machine Learning (CiML; NIPS Workshop),
pp. 1-4,
2018.
Abstract
Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and different opponent types. The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) competition is a new challenge that proposes research in this domain using multiple 3D games. The goal of this contest is to foster research in general agents that can learn across different games and opponent types, proposing a challenge as a milestone in the direction of Artificial General Intelligence.
Note
BibTex
@inproceedings{perez2018multi,
author: {Perez-Liebana, Diego and Hofmann, Katja and Mohanty, Sharada Prasanna and Kuno, Noburu and Kramer, Andre and Devlin, Sam and Gaina, Raluca D and Ionita, Daniel},
title: {{The Multi-Agent Reinforcement Learning in MalmO (MARLO) Competition}},
year: {2018},
booktitle: {{Challenges in Machine Learning (CiML; NIPS Workshop)}},
pages: {1--4},
eprint: {https://arxiv.org/abs/1901.08129},
abstract: {Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and different opponent types. The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) competition is a new challenge that proposes research in this domain using multiple 3D games. The goal of this contest is to foster research in general agents that can learn across different games and opponent types, proposing a challenge as a milestone in the direction of Artificial General Intelligence.},
}
Vanessa Volz, Dan Ashlock, Simon Colton, Steve Dahlskog, Jialin Liu, Simon M. Lucas, Diego Perez Liebana, Tommy Thompson,
"Gameplay Evaluation Measures",
in Dagstuhl Reports,
pp. 36-39,
2018.
Abstract
Note
BibTex
@inproceedings{measures2018dagstuhl,
author: {Vanessa Volz and Dan Ashlock and Simon Colton and Steve Dahlskog and Jialin Liu and Simon M. Lucas and Diego Perez Liebana and Tommy Thompson},
title: {{Gameplay Evaluation Measures}},
year: {2018},
journal: {{Dagstuhl Reports}},
booktitle: {{Artificial and Computational Intelligence in Games: AI-Driven Game Design (Dagstuhl Seminar 17471)}},
pages: {36--39},
editor: {Elisabeth Andre and Michael Cook and Mike Preuss and Pieter Spronck},
publisher: {Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
address: {Dagstuhl, Germany},
}
2017
Raluca D. Gaina, Jialin Liu, Simon M. Lucas, Diego Perez Liebana,
"Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing",
in Springer Lecture Notes in Computer Science, Applications of Evolutionary Computation, EvoApplications,
10199,
pp. 418-434,
2017.
Abstract
Monte Carlo Tree Search techniques have generally dominated General Video Game Playing, but recent research hasstarted looking at Evolutionary Algorithms and their potential at matching Tree Search level of play or even outperforming these methods. Online or Rolling Horizon Evolution is one of the options available to evolve sequences of actions for planning in General Video Game Playing, but no research has been done up to date that explores the capabilities of the vanilla version of this algorithm in multiple games. This study aims to critically analyse the different configurations regarding population size and individual length in a set of 20 games from the General Video Game AI corpus. Distinctions are made between deterministic and stochastic games, and the implications of using superior time budgets are studied. Results show that there is scope for the use of these techniques, which in some configurations outperform Monte Carlo Tree Search, and also suggest that further research in these methods could boost their performance.
Note
BibTex
@inproceedings{gaina2017rhanalysis,
author: {Raluca D. Gaina and Jialin Liu and Simon M. Lucas and Diego Perez Liebana},
title: {{Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing}},
year: {2017},
booktitle: {{Springer Lecture Notes in Computer Science, Applications of Evolutionary Computation, EvoApplications}},
volume: {10199},
pages: {418--434},
url: {https://link.springer.com/chapter/10.1007/978-3-319-55849-3_28},
abstract: {Monte Carlo Tree Search techniques have generally dominated General Video Game Playing, but recent research hasstarted looking at Evolutionary Algorithms and their potential at matching Tree Search level of play or even outperforming these methods. Online or Rolling Horizon Evolution is one of the options available to evolve sequences of actions for planning in General Video Game Playing, but no research has been done up to date that explores the capabilities of the vanilla version of this algorithm in multiple games. This study aims to critically analyse the different configurations regarding population size and individual length in a set of 20 games from the General Video Game AI corpus. Distinctions are made between deterministic and stochastic games, and the implications of using superior time budgets are studied. Results show that there is scope for the use of these techniques, which in some configurations outperform Monte Carlo Tree Search, and also suggest that further research in these methods could boost their performance.},
}
Raluca D. Gaina, Simon M. Lucas, Diego Perez Liebana,
"Rolling Horizon Evolution Enhancements in General Video Game Playing",
in Proceedings of IEEE Conference on Computational Intelligence and Games,
pp. 88-95,
Aug, 2017.
Abstract
Game AI literature has looked at applying various enhancements to Rolling Horizon Evolutionary methods or creating hybrids with popular tree search methods for an improved performance. However, these techniques have not been analyzed in depth in a general setting under the same conditions and restrictions. This paper proposes a fair juxtaposition of four enhancements applied to different parts of the evolutionary process: bandit-based mutation, a statistical tree for action selection, a shift buffer for population management and additional Monte Carlo simulations at the end of an individual’s evaluation. These methods are studied individually, as well as their hybrids, on a representative subset of 20 games of the General Video Game AI Framework and compared to the vanilla version of the Rolling Horizon Evolutionary Algorithm, in addition to the dominating Monte Carlo Tree Search. The results show that some of the enhancements are able to produce impressive results, while others fall short. Interesting hybrids also emerge, encouraging further research into this problem.
Note
BibTex
@inproceedings{gaina2017rhhybrids,
author: {Raluca D. Gaina and Simon M. Lucas and Diego Perez Liebana},
title: {{Rolling Horizon Evolution Enhancements in General Video Game Playing}},
year: {2017},
booktitle: {{Proceedings of IEEE Conference on Computational Intelligence and Games}},
month: {Aug},
pages: {88--95},
keywords: {computer games;evolutionary computation;Monte Carlo methods;tree searching;Rolling Horizon Evolutionary Algorithm;horizon evolution enhancements;Game AI literature;evolutionary process;statistical tree;action selection;shift buffer;General Video Game AI Framework;Monte Carlo Tree Search;Monte Carlo simulations;video game playing;population management;Games;Artificial intelligence;Evolutionary computation;Sociology;Monte Carlo methods;Mathematical model},
url: {http://ieeexplore.ieee.org/document/8080420/},
doi: {10.1109/CIG.2017.8080420},
abstract: {Game AI literature has looked at applying various enhancements to Rolling Horizon Evolutionary methods or creating hybrids with popular tree search methods for an improved performance. However, these techniques have not been analyzed in depth in a general setting under the same conditions and restrictions. This paper proposes a fair juxtaposition of four enhancements applied to different parts of the evolutionary process: bandit-based mutation, a statistical tree for action selection, a shift buffer for population management and additional Monte Carlo simulations at the end of an individual’s evaluation. These methods are studied individually, as well as their hybrids, on a representative subset of 20 games of the General Video Game AI Framework and compared to the vanilla version of the Rolling Horizon Evolutionary Algorithm, in addition to the dominating Monte Carlo Tree Search. The results show that some of the enhancements are able to produce impressive results, while others fall short. Interesting hybrids also emerge, encouraging further research into this problem.},
}
Raluca D. Gaina, Simon M. Lucas, Diego Perez Liebana,
"Population Seeding Techniques for Rolling Horizon Evolution in General Video Game Playing",
in Proceedings of the Congress on Evolutionary Computation,
pp. 1956-1963,
June, 2017.
Abstract
While Monte Carlo Tree Search and closely related methods have dominated General Video Game Playing, recent research has demonstrated the promise of Rolling Horizon Evolutionary Algorithms as an interesting alternative. However, thereislittleattentionpaidtopopulationinitializationtechniques in the setting of general real-time video games. Therefore, this paper proposes the use of population seeding to improve the performance of Rolling Horizon Evolution and presents the results of two methods, One Step Look Ahead and Monte Carlo Tree Search, tested on 20 games of the General Video Game AI corpus with multiple evolution parameter values (population size and individual length). An in-depth analysis is carried out between the results of the seeding methods and the vanilla Rolling Horizon Evolution. In addition, the paper presents a comparison to a Monte Carlo Tree Search algorithm. The results are promising, with seeding able to boost performance significantly over baseline evolution and even match the high level of play obtained by the Monte Carlo Tree Search.
Note
BibTex
@inproceedings{gaina2017rhseeding,
author: {Raluca D. Gaina and Simon M. Lucas and Diego Perez Liebana},
title: {{Population Seeding Techniques for Rolling Horizon Evolution in General Video Game Playing}},
year: {2017},
booktitle: {{Proceedings of the Congress on Evolutionary Computation}},
month: {June},
pages: {1956--1963},
keywords: {computer games;evolutionary computation;Monte Carlo methods;tree searching;population seeding techniques;general video game playing;rolling horizon evolutionary algorithms;population initialization techniques;one step look ahead;Monte Carlo tree search algorithm;Games;Sociology;Monte Carlo methods;Artificial intelligence;Algorithm design and analysis;Evolutionary computation},
url: {http://ieeexplore.ieee.org/document/7969540/},
doi: {10.1109/CEC.2017.7969540},
abstract: {While Monte Carlo Tree Search and closely related methods have dominated General Video Game Playing, recent research has demonstrated the promise of Rolling Horizon Evolutionary Algorithms as an interesting alternative. However, thereislittleattentionpaidtopopulationinitializationtechniques in the setting of general real-time video games. Therefore, this paper proposes the use of population seeding to improve the performance of Rolling Horizon Evolution and presents the results of two methods, One Step Look Ahead and Monte Carlo Tree Search, tested on 20 games of the General Video Game AI corpus with multiple evolution parameter values (population size and individual length). An in-depth analysis is carried out between the results of the seeding methods and the vanilla Rolling Horizon Evolution. In addition, the paper presents a comparison to a Monte Carlo Tree Search algorithm. The results are promising, with seeding able to boost performance significantly over baseline evolution and even match the high level of play obtained by the Monte Carlo Tree Search.},
}
Raluca D. Gaina, Rokas Volkovas, Carlos Gonzalez Diaz, Rory Davidson,
"Automatic Game Tuning for Strategic Diversity",
in 2017 9th Computer Science and Electronic Engineering (CEEC),
pp. 195-200,
Sept, 2017.
Abstract
Finding the ideal game parameters is a common problem solved by game designers by manually tweaking game parameters. The aim is to ensure the desired gameplay outcomes for a specific game, a tedious process which could be alleviated through the use of Artificial Intelligence: using automatic game tuning. This paper presents an example of this process and introduces the concept of simulation based fitness evaluation focused on strategic diversity. A simple but effective Random Mutation Hill Climber algorithm is used to evolve a Zelda inspired game, by ensuring that agents using distinct heuristics are capable of achieving similar degrees of fitness. Two versions of the same game are presented to human players and their gameplay data is analyzed to identify whether they indeed find slightly more varied paths to the goal in the game evolved to be the more strategically diverse. Although the evolutionary process yields promising results, the human trials are unable to conclude a statistically significant difference between the two variants.
Note
BibTex
@inproceedings{gaina2017tuning,
author: {Raluca D. Gaina and Rokas Volkovas and Carlos Gonzalez Diaz and Rory Davidson},
title: {{Automatic Game Tuning for Strategic Diversity}},
year: {2017},
booktitle: {{2017 9th Computer Science and Electronic Engineering (CEEC)}},
month: {Sept},
pages: {195--200},
keywords: {artificial intelligence;computer games;evolutionary computation;game theory;genetic algorithms;automatic game tuning;strategic diversity;ideal game parameters;game designers;manually tweaking game parameters;Zelda inspired game;simulation-based fitness evaluation;effective Random Mutation Hill Climber algorithm;Games;Artificial intelligence;Tuning;Evolutionary computation;Algorithm design and analysis;Space exploration;Monte Carlo methods},
url: {http://ieeexplore.ieee.org/document/8101624/},
doi: {10.1109/CEEC.2017.8101624},
abstract: {Finding the ideal game parameters is a common problem solved by game designers by manually tweaking game parameters. The aim is to ensure the desired gameplay outcomes for a specific game, a tedious process which could be alleviated through the use of Artificial Intelligence: using automatic game tuning. This paper presents an example of this process and introduces the concept of simulation based fitness evaluation focused on strategic diversity. A simple but effective Random Mutation Hill Climber algorithm is used to evolve a Zelda inspired game, by ensuring that agents using distinct heuristics are capable of achieving similar degrees of fitness. Two versions of the same game are presented to human players and their gameplay data is analyzed to identify whether they indeed find slightly more varied paths to the goal in the game evolved to be the more strategically diverse. Although the evolutionary process yields promising results, the human trials are unable to conclude a statistically significant difference between the two variants.},
}
Kamolwan Kunanusont, Raluca D. Gaina, Jialin Liu, Simon M. Lucas, Diego Perez Liebana,
"The N-Tuple Bandit Evolutionary Algorithm for Game Improvement",
in Proc. of the IEEE Congress on Evolutionary Computation (CEC),
pp. 2201-2208,
June, 2017.
Abstract
This paper describes a new evolutionary algorithm that is especially well suited to AI-Assisted Game Design. The approach adopted in this paper is to use observations of AI agents playing the game to estimate the game's quality. Some of best agents for this purpose are General Video Game AI agents, since they can be deployed directly on a new game without game-specific tuning; these agents tend to be based on stochastic algorithms which give robust but noisy results and tend to be expensive to run. This motivates the main contribution of the paper: the development of the novel N-Tuple Bandit Evolutionary Algorithm, where a model is used to estimate the fitness of unsampled points and a bandit approach is used to balance exploration and exploitation of the search space. Initial results on optimising a Space Battle game variant suggest that the algorithm offers far more robust results than the Random Mutation Hill Climber and a Biased Mutation variant, which are themselves known to offer competitive performance across a range of problems. Subjective observations are also given by human players on the nature of the evolved games, which indicate a preference towards games generated by the N-Tuple algorithm.
Note
BibTex
@inproceedings{kunanusont2017ntuple,
author: {Kamolwan Kunanusont and Raluca D. Gaina and Jialin Liu and Simon M. Lucas and Diego Perez Liebana},
title: {{The N-Tuple Bandit Evolutionary Algorithm for Game Improvement}},
year: {2017},
booktitle: {{Proc. of the IEEE Congress on Evolutionary Computation (CEC)}},
month: {June},
pages: {2201--2208},
keywords: {computer games;evolutionary computation;mobile agents;search problems;N-tuple bandit evolutionary algorithm;automatic game improvement;AI-assisted game design;AI agents;game quality estimation;general video game AI agents;stochastic algorithms;fitness estimation;unsampled points;search space exploitation;search space exploration;Space Battle game optimisation;Games;Artificial intelligence;Evolutionary computation;Aerospace electronics;Marine vehicles;Missiles;Tuning},
url: {http://ieeexplore.ieee.org/document/7969571/},
doi: {10.1109/CEC.2017.7969571},
abstract: {This paper describes a new evolutionary algorithm that is especially well suited to AI-Assisted Game Design. The approach adopted in this paper is to use observations of AI agents playing the game to estimate the game's quality. Some of best agents for this purpose are General Video Game AI agents, since they can be deployed directly on a new game without game-specific tuning; these agents tend to be based on stochastic algorithms which give robust but noisy results and tend to be expensive to run. This motivates the main contribution of the paper: the development of the novel N-Tuple Bandit Evolutionary Algorithm, where a model is used to estimate the fitness of unsampled points and a bandit approach is used to balance exploration and exploitation of the search space. Initial results on optimising a Space Battle game variant suggest that the algorithm offers far more robust results than the Random Mutation Hill Climber and a Biased Mutation variant, which are themselves known to offer competitive performance across a range of problems. Subjective observations are also given by human players on the nature of the evolved games, which indicate a preference towards games generated by the N-Tuple algorithm.},
}
Diego Perez Liebana, Matthew Stephenson, Raluca D. Gaina, Jochen Renz, Simon M. Lucas,
"Introducing Real World Physics and Macro-Actions to General Video Game AI",
in Proceedings of IEEE Conference on Computational Intelligence and Games,
pp. 248-255,
Aug, 2017.
Abstract
The General Video Game AI Framework has featured multiple games and several tracks since the first competition in 2014. Although the games of the framework are very assorted in nature, there is an underlying commonality with respect to the physics that govern the game: all of them are based on a grid where the sprites make discrete movements, which is not expressive enough to cover any meaningful physics. This paper introduces an enhanced physics system that brings real-world physics such as friction, inertia and other forces to the framework. We also introduce macro-actions for the first time in GVGAI in two different controllers, Rolling Horizon Evolution and Monte Carlo Tree Search. Their usefulness is demonstrated inanewsetofgamesthatexploitsthesenewphysicsfeatures.Our results show that macro-actions can help controllers in certain situations and games, although there is a strong dependency on the game played when selecting which configuration fits best.
Note
BibTex
@inproceedings{perez2017macro-physics,
author: {Diego Perez Liebana and Matthew Stephenson and Raluca D. Gaina and Jochen Renz and Simon M. Lucas},
title: {{Introducing Real World Physics and Macro-Actions to General Video Game AI}},
year: {2017},
booktitle: {{Proceedings of IEEE Conference on Computational Intelligence and Games}},
month: {Aug},
pages: {248--255},
keywords: {computer games;Monte Carlo methods;tree searching;physics features;General Video Game AI Framework;enhanced physics system;real-world physics;macroactions;discrete movements;GVGAI;rolling horizon evolution;Monte Carlo tree search;Games;Sprites (computer);Artificial intelligence;Gravity;Friction;Avatars},
url: {http://ieeexplore.ieee.org/document/8080443/},
doi: {10.1109/CIG.2017.8080443},
abstract: {The General Video Game AI Framework has featured multiple games and several tracks since the first competition in 2014. Although the games of the framework are very assorted in nature, there is an underlying commonality with respect to the physics that govern the game: all of them are based on a grid where the sprites make discrete movements, which is not expressive enough to cover any meaningful physics. This paper introduces an enhanced physics system that brings real-world physics such as friction, inertia and other forces to the framework. We also introduce macro-actions for the first time in GVGAI in two different controllers, Rolling Horizon Evolution and Monte Carlo Tree Search. Their usefulness is demonstrated inanewsetofgamesthatexploitsthesenewphysicsfeatures.Our results show that macro-actions can help controllers in certain situations and games, although there is a strong dependency on the game played when selecting which configuration fits best.},
}
Khalifa, Ahmed, Green, Michael Cerny, Perez-Liebana, Diego, Togelius, Julian,
"General video game rule generation",
in Computational Intelligence and Games (CIG), 2017 IEEE Conference on,
pp. 170-177,
2017.
Abstract
Note
BibTex
@inproceedings{khalifa2017general,
author: {Khalifa, Ahmed and Green, Michael Cerny and Perez-Liebana, Diego and Togelius, Julian},
title: {{General video game rule generation}},
year: {2017},
booktitle: {{Computational Intelligence and Games (CIG), 2017 IEEE Conference on}},
pages: {170--177},
organization: {IEEE},
}
Philipp Rohlfshagen, Jialin Liu, Diego Perez-Liebana, Simon M. Lucas,
"Pac-Man Conquers Academia: Two Decades of Research Using a Classic Arcade Game",
in IEEE Transactions on Computational Intelligence and AI in Games,
2017.
Abstract
Note
BibTex
@article{rohlfshagen2017pacman,
author: {Philipp Rohlfshagen, Jialin Liu, Diego Perez-Liebana and Simon M. Lucas},
title: {{Pac-Man Conquers Academia: Two Decades of Research Using a Classic Arcade Game}},
year: {2017},
journal: {{IEEE Transactions on Computational Intelligence and AI in Games}},
doi: {10.1109/TG.2017.2737145},
}
Liu, Jialin, Perez-Liebana, Diego, Lucas, Simon M.,
"The Single-Player GVGAI Learning Framework - Technical Manual",
2017.
Abstract
Note
BibTex
@misc{liu2017learningmanual,
author: {Liu, Jialin and Perez-Liebana, Diego and Lucas, Simon M.},
title: {{The Single-Player GVGAI Learning Framework - Technical Manual}},
year: {2017},
url: {http://www.liujialin.tech/publications/GVGAISingleLearning_manual.pdf},
}
Guerrero-Romero, Cristina, Louis, Annie, Perez-Liebana, Diego,
"Beyond Playing to Win: Diversifying Heuristics for GVGAI",
in 2017 IEEE Conference on Computational Intelligence and Games (CIG),
2017.
Abstract
Note
BibTex
@inproceedings{guerrero2017beyondwin,
author: {Guerrero-Romero, Cristina and Louis, Annie and Perez-Liebana, Diego},
title: {{Beyond Playing to Win: Diversifying Heuristics for GVGAI}},
year: {2017},
booktitle: {{2017 IEEE Conference on Computational Intelligence and Games (CIG)}},
organization: {IEEE},
}
Ashlock, Daniel, Perez-Liebana, Diego, Saunders, Amanda,
"General Video Game Playing Escapes the No Free Lunch Theorem",
in Conference on Computational Intelligence and Games (CIG),
2017.
Abstract
Note
BibTex
@inproceedings{ashlock2017nofreelunch,
author: {Ashlock, Daniel and Perez-Liebana, Diego and Saunders, Amanda},
title: {{General Video Game Playing Escapes the No Free Lunch Theorem}},
year: {2017},
booktitle: {{Conference on Computational Intelligence and Games (CIG)}},
organization: {IEEE},
}
Gonzalez-Castro, Jose M, Perez-Liebana, Diego,
"Opponent Models Comparison for 2 Players in GVGAI Competitions",
in Computer Science and Electronic Engineering Conference, 2017 9th,
2017.
Abstract
Note
BibTex
@inproceedings{gonzalez2017oppmodels,
author: {Gonzalez-Castro, Jose M and Perez-Liebana, Diego},
title: {{Opponent Models Comparison for 2 Players in GVGAI Competitions}},
year: {2017},
booktitle: {{Computer Science and Electronic Engineering Conference, 2017 9th}},
organization: {IEEE},
}
Volz, Vanessa, Ashlock, Daniel, Colton, Simon, Dahlskog, Steve, Liu, Jialin, Lucas, Simon, Perez-Liebana, Diego, Thompson, Tommy,
"Gameplay Evaluation Measures",
in Dagstuhl Follow-Ups,
2017.
Abstract
Note
BibTex
@article{volz2017gameplay,
author: {Volz, Vanessa and Ashlock, Daniel and Colton, Simon and Dahlskog, Steve and Liu, Jialin and Lucas, Simon and Perez-Liebana, Diego and Thompson, Tommy},
title: {{Gameplay Evaluation Measures}},
year: {2017},
journal: {{Dagstuhl Follow-Ups}},
publisher: {Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik},
}
Perez-Liebana, Diego, Liu, Jialin, Lucas, Simon M,
"General Video Game AI as a Tool for Game Design",
2017.
Abstract
Note
BibTex
@misc{tutorial17cig,
author: {Perez-Liebana, Diego and Liu, Jialin and Lucas, Simon M},
title: {{General Video Game AI as a Tool for Game Design}},
year: {2017},
}
Liu, Jialin, Perez-Liebana, Diego, Lucas, Simon M,
"Bandit-based random mutation hill-climbing",
in Evolutionary Computation (CEC), 2017 IEEE Congress on,
pp. 2145-2151,
2017.
Abstract
Note
BibTex
@inproceedings{liu2017bandit,
author: {Liu, Jialin and Perez-Liebana, Diego and Lucas, Simon M},
title: {{Bandit-based random mutation hill-climbing}},
year: {2017},
booktitle: {{Evolutionary Computation (CEC), 2017 IEEE Congress on}},
pages: {2145--2151},
organization: {IEEE},
}