Minmax fuzzy deterministic policy gradient for zero-sum differential game: Take pursuit-evasion problem as example.
Wei LiaoXiaohui WeiJizhou LaiPublished in: J. Intell. Fuzzy Syst. (2021)
Keyphrases
- pursuit evasion
- policy gradient
- fuzzy sets
- game theory
- reinforcement learning
- fuzzy logic
- stochastic games
- fuzzy rules
- membership functions
- average reward
- optimal control
- gradient method
- boolean games
- neural network
- actor critic
- variance reduction
- fuzzy controller
- nash equilibrium
- function approximation
- markov decision processes
- search space