Filters








215,471 Hits in 4.2 sec

General Video Game Playing

John Levine, Clare Bates Congdon, Marc Ebner, Graham Kendall, Simon M. Lucas, Risto Miikkulainen, Tom Schaul, Tommy Thompson, Michael Wagner
2013 Dagstuhl Publications  
In this work, we seek to extend the idea of General Game Playing into the realm of video games, thus forming the area of General Video Game Playing (GVGP).  ...  In the area of games, this has given rise to the challenge of General Game Playing (GGP).  ...  Games for General Video Game Playing What kind of games are suitable for General Video Game Playing research?  ... 
doi:10.4230/dfu.vol6.12191.77 dblp:conf/dagstuhl/LevineCEKLMST13 fatcat:ud7gsnfozfam5d5gtbkqbibemy

Neuroevolution for General Video Game Playing

Spyridon Samothrakis, Diego Perez-Liebana, Simon M. Lucas, Maria Fasli
2015 2015 IEEE Conference on Computational Intelligence and Games (CIG)  
General Video Game Playing (GVGP) allows for the fair evaluation of algorithms and agents as it minimizes the ability of an agent to exploit apriori knowledge in the form of game specific heuristics.  ...  of games played increases.  ...  allow for a deeper analysis on their learning abilities in the domain of General Video Game Playing.  ... 
doi:10.1109/cig.2015.7317943 dblp:conf/cig/SamothrakisLLF15 fatcat:vmy2bx5625brdk3bcyz2uoknia

Reinforcement Learning with Dual-Observation for General Video Game Playing [article]

Chengpeng Hu, Ziqi Wang, Tianye Shu, Hao Tong, Julian Togelius, Xin Yao, Jialin Liu
2022 arXiv   pre-print
The General Video Game AI Learning Competition aims at designing agents that are capable of learning to play different game levels that were unseen during training.  ...  Reinforcement learning algorithms have performed well in playing challenging board and video games.  ...  (i) We present a robust RL agent, called Arcane, for general video game playing.  ... 
arXiv:2011.05622v3 fatcat:sjgph5shj5gunlbcxtpvm2237u

Evaluating Generalisation in General Video Game Playing [article]

Martin Balla and Simon M. Lucas and Diego Perez-Liebana
2020 arXiv   pre-print
The General Video Game Artificial Intelligence (GVGAI) competition has been running for several years with various tracks.  ...  We found that solely using the rewards provided by the game might not encourage winning.  ...  It is developed with the objective of centering research in general video game playing.  ... 
arXiv:2005.11247v1 fatcat:7jr6yqikized5peugjcf3kyk24

Learning to Play General Video-Games via an Object Embedding Network [article]

William Woof, Ke Chen
2018 arXiv   pre-print
Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI.  ...  However most current DRL video-game agents learn end-to-end from the video-output of the game, which is superfluous for many applications and creates a number of additional problems.  ...  INTRODUCTION General video-game AI (GVG-AI) is an area regarding the development of general algorithms that enable AI agents to play a wide range of different video-games with minimal tailoring to specific  ... 
arXiv:1803.05262v2 fatcat:zqjfuoc3hredxo4wju2jkthnsi

Rolling Horizon Evolutionary Algorithms for General Video Game Playing [article]

Raluca D. Gaina, Sam Devlin, Simon M. Lucas, Diego Perez-Liebana
2020 arXiv   pre-print
Game-playing Evolutionary Algorithms, specifically Rolling Horizon Evolutionary Algorithms, have recently managed to beat the state of the art in win rate across many video games.  ...  We then use a parameter optimiser, the N-Tuple Bandit Evolutionary Algorithm, to find the best combination of parameters in 20 games from the General Video Game AI Framework.  ...  ACKNOWLEDGMENTS This work was funded by the EPSRC CDT in Intelligent Games and Game Intelligence (IGGI) EP/L015846/1  ... 
arXiv:2003.12331v2 fatcat:mcm3xm5qgjawjgbv2h3lnkpgvm

Rolling Horizon NEAT for General Video Game Playing

Diego Perez-Liebana, Muhammad Sajid Alam, Raluca D. Gaina
2020 2020 IEEE Conference on Games (CoG)  
The algorithm proposed here is general and introduces a new way of representing information within rolling horizon evolution techniques.  ...  Although results are overall not better than other SFP methods, the nature of rhNEAT to adapt to changing game features has allowed to establish new state of the art records in games that other methods  ...  Win rates per game for rhNEAT, MCTS, RHEA and state of the art results for rolling horizon methods. Graphs [26]  ... 
doi:10.1109/cog47356.2020.9231606 dblp:conf/cig/LiebanaAG20 fatcat:w455qc4u5felhj42fwha2n27vi

Rolling Horizon NEAT for General Video Game Playing [article]

Diego Perez-Liebana, Muhammad Sajid Alam, Raluca D. Gaina
2020 arXiv   pre-print
The algorithm proposed here is general and introduces a new way of representing information within rolling horizon evolution techniques.  ...  Although results are overall not better than other SFP methods, the nature of rhNEAT to adapt to changing game features has allowed to establish new state of the art records in games that other methods  ...  Win rates per game for rhNEAT, MCTS, RHEA and state of the art results for rolling horizon methods. Graphs [26]  ... 
arXiv:2005.06764v1 fatcat:roqsg6isejdj3i4qdol7o5awd4

Open Loop Search for General Video Game Playing

Diego Perez Liebana, Jens Dieskau, Martin Hunermund, Sanaz Mostaghim, Simon Lucas
2015 Proceedings of the 2015 on Genetic and Evolutionary Computation Conference - GECCO '15  
General Video Game Playing is a sub-field of Game Artificial Intelligence, where the goal is to find algorithms capable of playing many different real-time games, some of them unknown a priori.  ...  Research in this area has been of special interest in the last years, with emerging contests like the General Video Game AI (GVG-AI) Competition.  ...  General Game Playing (GGP) and General Video Game Playing (GVGP), on the other hand, drive research to algorithms that play a set of significantly different games, even some of them unknown a priori.  ... 
doi:10.1145/2739480.2754811 dblp:conf/gecco/LiebanaDHML15 fatcat:fc7rxqarlzfj7pyubphrl4gsgq

Investigating MCTS modifications in general video game playing

Frederik Frydenberg, Kasper R. Andersen, Sebastian Risi, Julian Togelius
2015 2015 IEEE Conference on Computational Intelligence and Games (CIG)  
This paper investigates of how well these modifications perform in general video game playing using the general video game AI (GVG-AI) framework and introduces a new MCTS modification called UCT reverse  ...  being played.  ...  General Video Game Playing The AAAI general game playing competition by Stanford Logic Group of Stanford University [7] is one of the oldest and most well-known general game playing frameworks.  ... 
doi:10.1109/cig.2015.7317937 dblp:conf/cig/FrydenbergART15 fatcat:25txwjyixragrcxvpa3ngezxj4

Ensemble Decision Systems for General Video Game Playing

Damien Anderson, Philip Rodgers, John Levine, Cristina Guerrero-Romero, Diego Perez-Liebana
2019 2019 IEEE Conference on Games (CoG)  
options for building an Ensemble Decision System as well as providing analysis on its performance compared to the individual components of the system with interesting results, showing an increase in the generality  ...  ACKNOWLEDGMENT This work was partially funded by the EPSRC CDT in Intelligent Games and Game Intelligence (IGGI) EP/L015846/1.  ...  BACKGROUND The field of General Video Game Playing (GVGP) began in 2013 as a way of promoting interest towards developing game playing agents that could play a wide variety of video games [1] .  ... 
doi:10.1109/cig.2019.8848089 dblp:conf/cig/AndersonRLGL19 fatcat:2r5hndartbfohpijpknqulpgaq

Reuse of Neural Modules for General Video Game Playing [article]

Alexander Braylan, Mark Hollenbeck, Elliot Meyerson, Risto Miikkulainen
2015 arXiv   pre-print
can be predicted based on a high-level characterization of game dynamics.  ...  This approach is more general than previous approaches to neural transfer for reinforcement learning.  ...  It will be interesting to investigate whether the same principles extend to other general video game playing platforms, such as VGDL (Perez et al. 2015; Schaul 2013) .  ... 
arXiv:1512.01537v1 fatcat:t6i5qmlpcfcv3frh3np4xa6d44

Shallow decision-making analysis in General Video Game Playing [article]

Ivan Bravi, Jialin Liu, Diego Perez-Liebana, Simon Lucas
2018 arXiv   pre-print
The General Video Game AI competitions have been the testing ground for several techniques for game playing, such as evolutionary computation techniques, tree search algorithms, hyper heuristic based or  ...  So far the metrics used to evaluate the performance of agents have been win ratio, game score and length of games.  ...  INTRODUCTION General video game playing (GVGP) and General game playing (GGP) aim at designing AI agents that are able to play more than one (video) game successfully alone without human intervention.  ... 
arXiv:1806.01151v1 fatcat:xjylowmawfeuzc5smdwfq4x3vy

Analyzing the robustness of general video game playing agents

Diego Perez-Liebana, Spyridon Samothrakis, Julian Togelius, Tom Schaul, Simon M. Lucas
2016 2016 IEEE Conference on Computational Intelligence and Games (CIG)  
This paper presents a study on the robustness and variability of performance of general video game-playing agents.  ...  Agents analyzed includes those that won the different legs of the 2014 and 2015 General Video Game AI Competitions, and two sample agents distributed with its framework.  ...  This framework is called the General Video Game AI Framework, and the competition the General Video Game AI Competition; both are abbreviated "GVGAI".  ... 
doi:10.1109/cig.2016.7860430 dblp:conf/cig/LiebanaSTSL16 fatcat:utqbnohotbfd7ckekal6rqjidi

Reuse of Neural Modules for General Video Game Playing

Alexander Braylan, Mark Hollenbeck, Elliot Meyerson, Risto Miikkulainen
2016 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
can be predicted based on a high-level characterization of game dynamics.  ...  This approach is more general than previous approaches to neural transfer for reinforcement learning.  ...  It will be interesting to investigate whether the same principles extend to other general video game playing platforms, such as VGDL (Perez et al. 2015; Schaul 2013) .  ... 
doi:10.1609/aaai.v30i1.10014 fatcat:t6267vxzezcsxfnja4sfneul54
« Previous Showing results 1 — 15 out of 215,471 results