BiC-DDPG: Bidirectionally-Coordinated Nets for Deep Multi-agent Reinforcement Learning.
Gongju WangDianxi ShiChao XueHao JiangYajie WangPublished in: CollaborateCom (2) (2020)
Keyphrases
- multi agent reinforcement learning
- multi agent
- learning agents
- cooperative
- bayesian information criterion
- model selection
- maximum likelihood
- multi agent systems
- multi agent learning
- reinforcement learning
- stochastic games
- software agents
- search space
- single agent
- agent interactions
- autonomous agents
- multiagent systems
- knowledge based systems
- distributed control