Exploration via Joint Policy Diversity for Sparse-Reward Multi-Agent Tasks.
Pei XuJunge ZhangKaiqi HuangPublished in: IJCAI (2023)
Keyphrases
- multi agent
- reinforcement learning
- partially observable environments
- multi agent environments
- optimal policy
- cooperative
- action selection
- exploration exploitation tradeoff
- sparse data
- transfer learning
- multi agent systems
- reward function
- multi objective
- compressive sensing
- policy iteration
- team formation
- inverse reinforcement learning
- high dimensional
- total reward
- face recognition