Mutual-Information Regularized Multi-Agent Policy Iteration.
Jiangxing WangDeheng YeZongqing LuPublished in: NeurIPS (2023)
Keyphrases
- policy iteration
- mutual information
- multi agent
- reinforcement learning
- least squares
- markov decision processes
- model free
- fixed point
- optimal policy
- sample path
- policy evaluation
- temporal difference
- image registration
- finite state
- similarity measure
- feature selection
- markov decision process
- average reward
- infinite horizon
- multi agent systems
- state space
- function approximation
- convergence rate
- single agent
- optimal control
- multiple agents
- reinforcement learning algorithms
- objective function