Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning.
Xiangxiang ChuHangjun YePublished in: CoRR (2017)
Keyphrases
- multi agent reinforcement learning
- policy gradient
- reinforcement learning
- cooperative
- multi agent
- multi agent learning
- multi agent systems
- learning agents
- function approximation
- gradient method
- stochastic games
- reinforcement learning algorithms
- single agent
- optimal control
- variance reduction
- mobile robot
- machine learning
- average reward
- multiple agents
- learning problems
- monte carlo