Fuzzy Policy Reinforcement Learning in Cooperative Multi-robot Systems.
Dongbing GuErfu YangPublished in: J. Intell. Robotic Syst. (2007)
Keyphrases
- multi robot systems
- cooperative
- reinforcement learning
- multi agent
- optimal policy
- multi robot
- markov decision process
- fuzzy sets
- policy search
- mobile robot
- autonomous robots
- action selection
- function approximation
- actor critic
- fuzzy logic
- markov decision processes
- policy gradient
- membership functions
- multi agent systems
- dynamic programming
- state space
- control policy
- multiple robots
- temporal difference
- reinforcement learning algorithms
- reward function
- genetic algorithm
- fuzzy rules
- fuzzy numbers
- real robot
- function approximators
- fuzzy neural network
- computer vision
- real time
- neural network