Centralized reinforcement learning for multi-agent cooperative environments.
Chengxuan LuQihao BaoShaojie XiaChongxiao QuPublished in: Evol. Intell. (2024)
Keyphrases
- reinforcement learning
- model free
- state space
- multi agent environments
- function approximation
- dynamic environments
- real world
- reinforcement learning algorithms
- machine learning
- peer to peer
- markov decision processes
- data sets
- dynamic programming
- supervised learning
- digital libraries
- computing environments
- information systems
- optimal control
- learning algorithm
- partially observable