Conservative Offline Policy Adaptation in Multi-Agent Games.
Chengjie WuPingzhong TangJun YangYujing HuTangjie LvChangjie FanChongjie ZhangPublished in: NeurIPS (2023)
Keyphrases
- multi agent
- leader follower
- learning agents
- extensive form games
- game theory
- multi agent systems
- multi agent decision making
- optimal policy
- reinforcement learning agents
- cooperative
- game theoretic
- reinforcement learning
- perfect information
- stochastic games
- multiagent systems
- autonomous agents
- video games
- nash equilibria
- real time
- game playing
- single agent
- intelligent agents
- computer games
- digital games
- game design
- game play
- serious games
- nash equilibrium
- multiple agents
- human computation
- e learning
- cooperative agents
- heterogeneous agents
- monte carlo tree search
- educational games
- coalitional games
- imperfect information
- coalition formation
- online game