Linguistic Reward-orientated Takagi-Sugeno Fuzzy Reinforcement Learning.
Xionghuawei YanZhidong DengZengqi SunPublished in: FUZZ-IEEE (2001)
Keyphrases
- reinforcement learning
- takagi sugeno fuzzy
- steady state
- function approximation
- exponential stability
- eligibility traces
- state space
- model free
- average reward
- learning algorithm
- partially observable environments
- reinforcement learning algorithms
- reward function
- sufficient conditions
- dynamic programming
- control policy
- optimal control
- action selection
- markov decision process
- learning agent
- neural network
- temporal difference
- markov decision processes