Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning.
Yuchen XiaoWeihao TanChristopher AmatoPublished in: NeurIPS (2022)
Keyphrases
- multi agent reinforcement learning
- actor critic
- reinforcement learning
- policy gradient
- reinforcement learning algorithms
- temporal difference
- optimal control
- multi agent
- function approximation
- state space
- gradient method
- neuro fuzzy
- learning agents
- stochastic games
- model free
- learning agent
- dynamic programming
- machine learning
- action selection
- neural network
- learning automata
- markov decision processes
- learning algorithm
- kernel methods
- learning capabilities
- single agent
- policy iteration
- optimal policy
- least squares
- multi agent systems