Entropy-Guided Exploration in AlphaZero: Enhancing MCTS with Information Gain for Strategic Decision Making
Pages 151 - 156
Abstract
AlphaZero has revolutionized AI game-playing, yet it may overlook actions crucial for long-term strategy. This paper introduces Entropy-Guided MCTS (EG-MCTS), enhancing AlphaZero by incorporating information theory into action selection. We propose an information gain metric based on game state entropy, integrating it into MCTS to balance immediate rewards with informational value. Our contributions include developing this metric, modifying neural network training, and systematically balancing information gain with existing criteria. Comprehensive evaluations across various games demonstrate EG-MCTS's improved performance in complex strategic scenarios, showing enhanced efficiency in game tree navigation and adaptation to unfamiliar situations. These findings suggest broader applications in sequential decision-making under uncertainty, advancing the development of more adaptable AI systems.
References
[1]
Świechowski, Maciej, et al. "Monte Carlo tree search: A review of recent modifications and applications." Artificial Intelligence Review 56.3 (2023): 2497-2562.
[2]
Coulom, Rémi. "Efficient selectivity and backup operators in Monte-Carlo tree search." International conference on computers and games. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006.
[3]
Houthooft, Rein, et al. "Vime: Variational information maximizing exploration." Advances in neural information processing systems 29 (2016).
[4]
Kocsis, Levente, and Csaba Szepesvári. "Bandit based monte-carlo planning." European conference on machine learning. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006.
[5]
Silver, David, et al. "Mastering the game of go without human knowledge." nature 550.7676 (2017): 354-359.
[6]
Schrittwieser, Julian, et al. "Mastering atari, go, chess and shogi by planning with a learned model." Nature 588.7839 (2020): 604-609.
[7]
Niu, Yazhe, et al. "LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios." Advances in Neural Information Processing Systems 36 (2024).
[8]
Świechowski, Maciej, et al. "Monte Carlo tree search: A review of recent modifications and applications." Artificial Intelligence Review 56.3 (2023): 2497-2562.
[9]
Sutton, Richard S., and Andrew G. Barto. "Reinforcement learning: An introduction." MIT press, 2018.
[10]
Gelly, Sylvain, and David Silver. "Combining online and offline knowledge in UCT." Proceedings of the 24th international conference on machine learning. 2007.
[11]
Chaslot, Guillaume, et al. "Monte-carlo tree search: A new framework for game ai." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. Vol. 4. No. 1. 2008.
[12]
Browne, Cameron B., et al. "A survey of Monte Carlo tree search methods." IEEE Transactions on Computational Intelligence and AI in games 4.1 (2012): 1-43.
[13]
Lanctot, Marc, et al. "A unified game-theoretic approach to multiagent reinforcement learning." Advances in Neural Information Processing Systems. 2017.
[14]
Mnih, Volodymyr, et al. "Human-level control through deep reinforcement learning." Nature 518.7540 (2015): 529-533.
[15]
Pirnay, Jonathan, and Dominik G. Grimm. "Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but Improvement." arXiv preprint arXiv:2403.15180 (2024).
[16]
Francisco-Valencia, Iván, José Raymundo Marcial-Romero, and Rosa María Valdovinos-Rosas. "A comparison between UCB and UCB-Tuned as selection policies in GGP." Journal of Intelligent & Fuzzy Systems 36.5 (2019): 5073-5079.
[17]
Lisy, Viliam, et al. "Convergence of Monte Carlo tree search in simultaneous move games." Advances in Neural Information Processing Systems 26 (2013).
[18]
Whitehouse, Daniel. Monte Carlo tree search for games with hidden information and uncertainty. Diss. University of York, 2014.
[19]
Phan, Thomy, et al. "Adaptive Anytime Multi-Agent Path Finding Using Bandit-Based Large Neighborhood Search." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38. No. 16. 2024.
[20]
Zhou, Andy, et al. "Language agent tree search unifies reasoning acting and planning in language models." arXiv preprint arXiv:2310.04406 (2023).
[21]
Houlsby, Neil, et al. "Bayesian active learning for classification and preference learning." arXiv preprint arXiv:1112.5745 (2011).
[22]
Hernández-Lobato, José Miguel, Matthew W. Hoffman, and Zoubin Ghahramani. "Predictive entropy search for efficient global optimization of black-box functions." Advances in neural information processing systems 27 (2014).
[23]
Shannon, Claude Elwood. "A mathematical theory of communication." The Bell system technical journal 27.3 (1948): 379-423.
[24]
LeCun, Yann, et al. "Gradient-based learning applied to document recognition." Proceedings of the IEEE 86.11 (1998): 2278-2324.
[25]
He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
[26]
Matsuzaki, Kiminori. "Empirical analysis of PUCT algorithm with evaluation functions of different quality." 2018 Conference on Technologies and Applications of Artificial Intelligence (TAAI). IEEE, 2018.
Index Terms
- Entropy-Guided Exploration in AlphaZero: Enhancing MCTS with Information Gain for Strategic Decision Making
Recommendations
A Monte Carlo Neural Fictitious Self-Play approach to approximate Nash Equilibrium in imperfect-information dynamic games
AbstractSolving the optimization problem to approach a Nash Equilibrium point plays an important role in imperfect information games, e.g., StarCraft and poker. Neural Fictitious Self-Play (NFSP) is an effective algorithm that learns approximate Nash ...
Evolutionary learning of policies for MCTS simulations
FDG '12: Proceedings of the International Conference on the Foundations of Digital GamesMonte-Carlo Tree Search (MCTS) grows a partial game tree and uses a large number of random simulations to approximate the values of the nodes. It has proven effective in games with such as Go and Hex where the large search space and difficulty of ...
The art of drafting: a team-oriented hero recommendation system for multiplayer online battle arena games
RecSys '18: Proceedings of the 12th ACM Conference on Recommender SystemsMultiplayer Online Battle Arena (MOBA) games have received increasing popularity recently. In a match of such games, players compete in two teams of five, each controlling an in-game avatar, known as heroes, selected from a roster of more than 100. The ...
Comments
Information & Contributors
Information
Published In
August 2024
306 pages
ISBN:9798400717833
DOI:10.1145/3696271
Copyright © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 02 December 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
MLMI 2024
MLMI 2024: 2024 The 7th International Conference on Machine Learning and Machine Intelligence (MLMI)
August 2 - 4, 2024
Osaka, Japan
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 47Total Downloads
- Downloads (Last 12 months)47
- Downloads (Last 6 weeks)23
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderFull Text
View this article in Full Text.
Full TextHTML Format
View this article in HTML Format.
HTML Format