Learning Progress Driven Multi-Agent Curriculum

arXiv:2205.10016v2 Announce Type: replace-cross
Abstract: Curriculum reinforcement learning (CRL) aims to speed up learning by gradually increasing the difficulty of a task, usually quantified by the achievable expected return. Inspired by the success of CRL in single-agent settings, a few works have attempted to apply CRL to multi-agent reinforcement learning (MARL) using the number of agents to control task difficulty. However, existing works typically use manually defined curricula such as a linear scheme. In this paper, we first apply state-of-the-art …

abstract agent apply arxiv cs.ai cs.lg cs.ma curriculum multi-agent progress reinforcement reinforcement learning speed success type