Distributed off-Policy Actor-Critic Reinforcement Learning with Policy Consensus.
Yan ZhangMichael M. ZavlanosPublished in: CoRR (2019)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- approximate dynamic programming
- optimal control
- reinforcement learning algorithms
- gradient method
- neuro fuzzy
- policy iteration
- multi agent
- function approximation
- policy gradient methods
- state space
- markov decision processes
- model free
- optimal policy
- control problems
- rl algorithms
- learning algorithm
- average reward
- linear program
- machine learning
- convergence rate
- supervised learning
- temporal difference learning
- dynamic programming