Abstract
As part of learning to play complex games, human players develop develop abstractions for concepts and strategies of gameplay consistent with game rules to improve their performance. These concepts are applied to explain other players' actions, and to inform their own actions in-game. Understanding other players' strategies is a crucial part of such improvement, but requires time and effort. In this paper, we propose a strategy similar to human cognition for training RL agents to synthesize learned strategies and policies as executable procedures based on sequences of gameplay actions. We present methods to automatically learn such programs to play chess and to solve tasks in a grid-based environment. We show that the learned strategies produce effective actions, and can be learned from gameplay data.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Krishnan, A., Potts, C. M., Jhala, A., Khadilkar, H., Karande, S., & Martens, C. (2026). Learning Explainable Representations of Complex Game-playing Strategies. https://omanscience.com/en/articles/learning-explainable-representations-of-complex-game-playing-strategies
MLA 9
Krishnan, Abhijeet, et al. "Learning Explainable Representations of Complex Game-playing Strategies." https://omanscience.com/en/articles/learning-explainable-representations-of-complex-game-playing-strategies.
Chicago (author–date)
Krishnan, Abhijeet, Colin M. Potts, Arnav Jhala, Harshad Khadilkar, Shirish Karande, and Chris Martens. 2026. "Learning Explainable Representations of Complex Game-playing Strategies." https://omanscience.com/en/articles/learning-explainable-representations-of-complex-game-playing-strategies.
Harvard
Krishnan, A., Potts, C. M., Jhala, A., Khadilkar, H., Karande, S. and Martens, C. (2026) 'Learning Explainable Representations of Complex Game-playing Strategies', Available at: https://omanscience.com/en/articles/learning-explainable-representations-of-complex-game-playing-strategies.
Vancouver
Krishnan A, Potts CM, Jhala A, Khadilkar H, Karande S, Martens C. Learning Explainable Representations of Complex Game-playing Strategies. https://omanscience.com/en/articles/learning-explainable-representations-of-complex-game-playing-strategies
IEEE
A. Krishnan, C. M. Potts, A. Jhala, H. Khadilkar, S. Karande, and C. Martens, "Learning Explainable Representations of Complex Game-playing Strategies," https://omanscience.com/en/articles/learning-explainable-representations-of-complex-game-playing-strategies.