Keyphrases
- actor critic
- multi agent
- reinforcement learning
- policy gradient
- temporal difference
- optimal control
- single agent
- approximate dynamic programming
- gradient method
- reinforcement learning algorithms
- neuro fuzzy
- policy iteration
- least squares
- function approximation
- multi agent systems
- model free
- state space
- cooperative
- average reward
- machine learning
- multiple agents
- optimal policy
- neural network
- partially observable markov decision processes
- evaluation function
- markov decision processes
- learning algorithm
- long run
- fuzzy rules
- decision making
- dynamical systems