Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning.
Jianzhun ShaoHongchang ZhangYuhang JiangShuncheng HeXiangyang JiPublished in: CoRR (2021)
Keyphrases
- multi agent reinforcement learning
- credit assignment
- policy gradient
- reinforcement learning
- multi agent
- function approximation
- stochastic games
- multi agent learning
- single agent
- gradient method
- average reward
- reinforcement learning algorithms
- optimal control
- cooperative
- state space
- multi agent systems
- function approximators
- model free
- learning algorithm
- optimal policy
- partially observable markov decision processes
- machine learning
- genetic algorithm
- supervised learning
- learning capabilities
- temporal difference
- markov decision processes
- learning problems
- text classification
- data mining