Fictitious Self-Play Reinforcement Learning with Expanding Value Estimation.
Chaohao HuYunlong CaiWeidong LiHongfei LiPublished in: RICAI (2023)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- estimation accuracy
- supervised learning
- state space
- case study
- multi agent
- least squares
- markov decision processes
- density estimation
- artificial intelligence
- optimal control
- estimation algorithm
- game playing
- model free
- reinforcement learning algorithms
- machine learning