Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing.
Xiangyu LiuKaiqing ZhangPublished in: CoRR (2023)
Keyphrases
- information sharing
- partially observable
- reinforcement learning
- multi agent
- partially observable domains
- state space
- markov decision processes
- partial observability
- share information
- decision problems
- dynamical systems
- partial observations
- action models
- data sharing
- government agencies
- markov decision problems
- reinforcement learning algorithms
- emergency response
- optimal policy
- e government
- function approximation
- infinite horizon
- reward function
- learning algorithm
- model free
- law enforcement
- fully observable
- machine learning
- virtual communities
- utility function
- partially observable markov decision processes
- heuristic search
- multiagent systems
- random walk
- information technology
- computational complexity
- partially observable environments