PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning

arXiv:2210.08872v2 Announce Type: replace-cross
Abstract: Centralized Training with Decentralized Execution (CTDE) has emerged as a widely adopted paradigm in multi-agent reinforcement learning, emphasizing the utilization of global information for learning an enhanced joint $Q$-function or centralized critic. In contrast, our investigation delves into harnessing global information to directly enhance individual $Q$-functions or individual actors. Notably, we discover that applying identical global information universally across all agents proves insufficient for optimal performance. Consequently, we advocate for the customization of global information …

abstract agent arxiv contrast cs.ai cs.lg cs.ma decentralized function global information investigation multi-agent paradigm personalized reinforcement reinforcement learning training type