The Partially Observable Asynchronous Multi-Agent Cooperation Challenge.
Meng YaoQiyue YinJun YangTongtong YuShengqi ShenJunge ZhangBin LiangKaiqi HuangPublished in: CoRR (2021)
Keyphrases
- partially observable
- multi agent cooperation
- state space
- decision problems
- markov decision processes
- reinforcement learning
- dynamical systems
- partial observability
- multi agent systems
- multi agent
- partially observable environments
- infinite horizon
- partial observations
- markov decision problems
- game theory
- planning domains
- belief state
- partially observable domains
- action models
- bayesian networks
- optimal policy
- partially observable markov decision processes
- reward function
- cooperative
- markov chain