Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning.
Yuchen XiaoXueguang LyuChristopher AmatoPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- actor critic
- multi agent
- temporal difference
- policy gradient
- function approximation
- reinforcement learning algorithms
- approximate dynamic programming
- markov decision processes
- state space
- optimal control
- learning algorithm
- average reward
- neuro fuzzy
- model free
- gradient method
- rl algorithms
- single agent
- transfer learning
- state action
- optimal policy
- dynamic programming
- policy iteration
- function approximators
- temporal difference learning
- supervised learning