A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning.
Qingxu FuTenghai QiuZhiqiang PuJianqiang YiWanmai YuanPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- multi agent
- cooperative
- multi agent systems
- function approximation
- multiagent systems
- state space
- gaussian graphical models
- reinforcement learning algorithms
- intelligent agents
- reward function
- directed graph
- graph representation
- graph theory
- learning algorithm
- eligibility traces
- temporal difference
- model free
- multiple agents
- random walk
- autonomous agents
- markov decision processes
- sparse data
- optimal policy
- sparse representation
- single agent
- learning process
- directed acyclic
- directed acyclic graph
- graph structure
- learning agents
- bipartite graph
- graph matching
- multiagent learning
- reinforcement learning methods
- structured data
- optimal control
- partially observable
- connected components
- continuous state
- finite state
- reward shaping
- signal recovery
- partially observable environments
- action selection
- spectral clustering