Learning Strategies for Imperfect Information Board Games Using Depth-Limited Counterfactual Regret Minimization and Belief State.
Chen ChenTomoyuki KanekoPublished in: CoG (2022)
Keyphrases
- learning strategies
- imperfect information
- perfect information
- regret minimization
- game theoretic
- belief state
- nash equilibrium
- board game
- game playing
- game theory
- online learning
- belief revision
- state space
- active learning
- decision problems
- game tree
- linear programming
- reinforcement learning
- dynamic bayesian networks
- trust model
- human players
- machine learning
- computer games
- knowledge base