Sample and Communication Efficient Fully Decentralized MARL Policy Evaluation via a New Approach: Local TD Update.
HairiZifan ZhangJia LiuPublished in: AAMAS (2024)
Keyphrases
- policy evaluation
- temporal difference
- least squares
- td learning
- multi agent reinforcement learning
- model free
- reinforcement learning
- reinforcement learning algorithms
- policy iteration
- cooperative
- multi agent
- evaluation function
- markov decision processes
- function approximation
- monte carlo
- model selection
- variance reduction
- machine learning