A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning.
Wesley SuttleZhuoran YangKaiqing ZhangZhaoran WangTamer BasarJi LiuPublished in: CoRR (2019)
Keyphrases
- multi agent
- reinforcement learning
- actor critic
- learning algorithm
- cost function
- dynamic programming
- search space
- gradient method
- optimal solution
- approximate dynamic programming
- state space
- simulated annealing
- particle swarm optimization
- machine learning
- policy gradient
- average reward
- model free
- neuro fuzzy
- convergence rate
- neural network
- np hard
- objective function
- multi agent systems