85 Hits in 9.0 sec

Word Play for Playing Othello (Reverses) [article]

Samantha E. Miller Noever, David Noever
2022 arXiv   pre-print
A primary contribution of these models magnifies (by two-fold) the previous record for player archives (120,000 human games over 45 years from 1977-2022), thus supplying the research community with more  ...  in gameplay (chess, Go, and checkers).  ...  ACKNOWLEDGEMENTS The authors would like to thank the PeopleTec Technical Fellows program for its encouragement and project assistance.  ... 
arXiv:2207.08766v1 fatcat:vjyqehhb4bcu5mkvt7xqf55ncy

Taking the Scenic Route: Automatic Exploration for Videogames [article]

Zeping Zhan, Batu Aytemiz, Adam M. Smith
2018 arXiv   pre-print
However, human gameplay data is expensive to acquire relative to the coverage of a game that it provides.  ...  We show that off-the-shelf automatic exploration strategies can explore with an effectiveness comparable to human gameplay on the same timescale.  ...  Monte Carlo Tree Search (MCTS) is one surprisingly simple and effective strategy for finding a sequence of moves in a modeled environment that approximately optimizes this score (Browne et al. 2012 )  ... 
arXiv:1812.03125v1 fatcat:onwiquqjzfau7atekmcnhvboe4

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  
The AI player then has to work out how to play the game and how to win.  ...  In the area of games, this has given rise to the challenge of General Game Playing (GGP).  ...  Two approaches to creating players are investigated, based on reinforcement learning [18] and Monte Carlo Tree Search [12] .  ... 
doi:10.4230/dfu.vol6.12191.77 dblp:conf/dagstuhl/LevineCEKLMST13 fatcat:ud7gsnfozfam5d5gtbkqbibemy

Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Search [article]

Anji Liu, Jianshu Chen, Mingze Yu, Yu Zhai, Xuewen Zhou, Ji Liu
2020 arXiv   pre-print
Monte Carlo Tree Search (MCTS) algorithms have achieved great success on many challenging benchmarks (e.g., Computer Go).  ...  These statistics are used to modify the UCT tree policy in the selection steps in a principled manner to retain effective exploration-exploitation tradeoff when we parallelize the most time-consuming expansion  ...  MONTE CARLO TREE SEARCH AND UPPER CONFIDENCE BOUND FOR TREES (UCT) We consider the Markov Decision Process (MDP) S, A, R, P, γ , where an agent interacts with the environment in order to maximize a long-term  ... 
arXiv:1810.11755v5 fatcat:bdzydkipsfbhfm7emblwukfjxa

Interactive Robot for Playing Russian Checkers

Ekaterina E. Kopets, Artur I. Karimov, Georgii Y. Kolev, Lorenzo Scalera, Denis N. Butusov
2020 Robotics  
Human–robot interaction in board games is a rapidly developing field of robotics.  ...  This paper presents a robot capable of playing Russian checkers designed for entertaining, training, and research purposes.  ...  Acknowledgments: The authors are grateful to M.Tech. student Andrey Ignatovskiy for preparing several program codes of AlphaZero algorithm used in this research.  ... 
doi:10.3390/robotics9040107 fatcat:cvh2w4nbnjfjvb2oq35cwa5rua

A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks [article]

Kun Wang, WaiChing Sun, Qiang Du
2020 arXiv   pre-print
The two agents automatically search for the Nash equilibrium of the meta-modeling game in an adversarial reinforcement learning framework without human intervention.  ...  We introduce an automated meta-modeling game where two competing AI agents systematically generate experimental data to calibrate a given constitutive model and to explore its weakness, in order to improve  ...  Initialize empty tree of the Monte Carlo Tree search (MCTS), set the temperature parameter τ train for "exploration and exploitation".  ... 
arXiv:2004.09392v1 fatcat:xcscbc2mufcczmoybj4a2hsqzy

Generalized Monte-Carlo Tree Search Extensions for General Game Playing

Hilmar Finnsson
Monte-Carlo Tree Search (MCTS) has proven an effective reasoning mechanism for this challenge, as is reflected by its popularity among designers of GGP agents.  ...  Providing GGP agents with the knowledge relevant to the game at hand in real time is, however, a challenging task.  ...  Monte-Carlo Tree Search MCTS uses its deliberation time to generate information from simulation rewards.  ... 
doi:10.1609/aaai.v26i1.8330 fatcat:zcfpe7wryzg6hnefo6bz5ia5he

The Go Transformer: Natural Language Modeling for Game Play [article]

Matthew Ciolino, David Noever, Josh Kalin
2020 arXiv   pre-print
Compared to random game boards, the GPT-2 fine-tuning shows efficient opening move sequences favoring corner play over less advantageous center and side play.  ...  Game generation as a language modeling task offers novel approaches to more than 40 other board games where historical text annotation provides training data (e.g., Amazons & Connect 4/6).  ...  We are grateful to the front-line emergency workers who do their difficult work during the COVID-19 pandemic.  ... 
arXiv:2007.03500v3 fatcat:jxbucewyeratvcykorhxd5hzzq

Fast Approximate Max-n Monte Carlo Tree Search for Ms Pac-Man

Spyridon Samothrakis, David Robles, Simon Lucas
2011 IEEE Transactions on Computational Intelligence and AI in Games  
We approached the problem by performing Monte-Carlo tree searches on a 5 player max n tree representation of the game with limited tree search depth.  ...  We present an application of Monte-Carlo Tree Search (MCTS) for the game of Ms Pac-Man.  ...  also based on Monte-Carlo Tree Search 5 .  ... 
doi:10.1109/tciaig.2011.2144597 fatcat:lfl3keghyjaaxayo7dj55jbyie

Winning Isn't Everything: Enhancing Game Development with Intelligent Agents [article]

Yunqi Zhao, Igor Borovikov, Fernando de Mesentier Silva, Ahmad Beirami, Jason Rupert, Caedmon Somers, Jesse Harder, John Kolen, Jervis Pinto, Reza Pourabolghasem, James Pestrak, Harold Chaput (+5 others)
2020 arXiv   pre-print
Recently, there have been several high-profile achievements of agents learning to play games against humans and beat them.  ...  Unlike the agents built to "beat the game", our agents aim to produce human-like behavior to help with game evaluation and balancing.  ...  The authors also would like to thank the anonymous reviewers and the EIC for their constructive feedback.  ... 
arXiv:1903.10545v5 fatcat:v2vc7pxzvrfbbiezdttz7mfyze

Using a Surrogate Model of Gameplay forAutomated Level Design

Daniel Karavolos, Antonios Liapis, Georgios N Yannakakis
2018 Zenodo  
This opens up potential applications for a designer tool which can adapt a human authored map to fit the designer's desired gameplay outcomes, taking account of the game's rule  ...  We use a deep learning approach to train a model on simulated play throughs of two-player death match games, in diverse levels and with different character classes per player.  ...  Such agents are often simplistic (including those used in this paper), but agents may use more general gameplaying algorithms such as Monte-Carlo Tree Search [13] or may have different goals depending  ... 
doi:10.5281/zenodo.2567174 fatcat:jv4nzn6cmzez3ir3yoq4lb6faa

Towards generating arcade game rules with VGDL

Thorbjorn S. Nielsen, Gabriella A. B. Barros, Julian Togelius, Mark J. Nelson
2015 2015 IEEE Conference on Computational Intelligence and Games (CIG)  
players to play better than bad players.  ...  For the purpose of such evaluations, we introduce two new game tree search algorithms, DeepSearch and Explorer; these perform very well on benchmark games and constitute a substantial subsidiary contribution  ...  Thanks to Diego Perez, Spyros Samothrakis, Tom Schaul, and Simon Lucas for useful discussions.  ... 
doi:10.1109/cig.2015.7317941 dblp:conf/cig/NielsenBTN15 fatcat:sxhdtmm4ercipmrghdd7j4fewy

Exploring Gameplay With AI Agents [article]

Fernando de Mesentier Silva, Igor Borovikov, John Kolen, Navid Aghdaie, Kazi Zaman
2018 arXiv   pre-print
Our agent is able to play in minutes what would take testers days of organic gameplay.  ...  In this paper, we present a playtesting approach that explores the game space with automated agents and collects data to answer questions posed by the designers.  ...  The Monte Carlo Tree Search algorithm could be a viable alternative eliminating this overhead of making a new heuristic in favor of a custom win condition for each experiment.  ... 
arXiv:1811.06962v1 fatcat:bcnfbth5ijaqfjaslq4ramkkne

Enhancements for Monte-Carlo Tree Search in Ms Pac-Man

Tom Pepels, Mark H. M. Winands
2012 2012 IEEE Conference on Computational Intelligence and Games (CIG)  
In this paper enhancements for the Monte-Carlo Tree Search (MCTS) framework are investigated to play Ms Pac-Man.  ...  Furthermore, the Pac-Man agent has to compete with a range of different ghost agents, hence limited assumptions can be made about the opponent's behaviour.  ...  MONTE-CARLO TREE SEARCH Monte-Carlo Tree Search (MCTS) is a best-first search method based on random sampling by Monte-Carlo simulations of the state space for a certain domain [18, 19] .  ... 
doi:10.1109/cig.2012.6374165 dblp:conf/cig/PepelsW12 fatcat:2ayz3gmvwrffdevmz2pjad5vwe

A Panorama of Artificial and Computational Intelligence in Games

Georgios N. Yannakakis, Julian Togelius
2015 IEEE Transactions on Computational Intelligence and AI in Games  
We view and analyze the areas from three key perspectives: (1) the dominant AI method(s) used under each area; (2) the relation of each area with respect to the end (human) user; and (3) the placement  ...  This paper attempts to give a high-level overview of the field of artificial and computational intelligence (AI/CI) in games, with particular reference to how the different core research areas within this  ...  ACKNOWLEDGMENTS Thanks to the participants of Dagstuhl seminar 12191, and our various collaborators and students for seeding many of the ideas that went into this paper. Special thanks to Mirjam P.  ... 
doi:10.1109/tciaig.2014.2339221 fatcat:vyni6ub7rbakpi53zlojuhpzym
« Previous Showing results 1 — 15 out of 85 results