Off-Policy Multi-Agent Decomposed Policy Gradients.
Yihan WangBeining HanTonghan WangHeng DongChongjie ZhangPublished in: CoRR (2020)
Keyphrases
- multi agent
- multi agent systems
- intelligent agents
- reinforcement learning
- cooperative
- optimal policy
- multiagent systems
- autonomous agents
- agent oriented
- software agents
- policy making
- learning algorithm
- allocation policy
- state dependent
- policy makers
- multiple agents
- coalition formation
- data sets
- image gradient
- asymptotically optimal
- expected cost
- infinite horizon
- heterogeneous agents
- management policies
- team formation
- policy search
- agent based simulations