RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning.
Boning LiZhixuan FangLongbo HuangPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- extensive form games
- imperfect information
- imperfect information games
- influence diagrams
- multi agent
- game theoretic
- decision problems
- function approximation
- action selection
- optimal policy
- partially observable domains
- reinforcement learning algorithms
- model free
- game playing
- action space
- state space
- game tree search
- markov decision processes
- game theory
- temporal difference
- perfect information
- card game
- stochastic games
- learning algorithm
- partially observable
- machine learning
- function approximators
- game tree
- rl algorithms
- sensitivity analysis
- agent learns
- multi agent systems
- cooperative
- alternating time temporal logic