2 papers
cs.LG2023
Model-Based Decentralized Policy Optimization
Hao Luo, Jiechuan Jiang, Zongqing Lu
Decentralized policy optimization has been commonly used in cooperative multi-agent tasks. However, since all agents are updating their policies simultaneously, from the perspectiv…
cs.LG2023
Best Possible Q-Learning
Jiechuan Jiang, Zongqing Lu
Fully decentralized learning, where the global information, i.e., the actions of other agents, is inaccessible, is a fundamental challenge in cooperative multi-agent reinforcement…