Cautiously-Optimistic Knowledge Sharing for Cooperative Multi-Agent Reinforcement Learning

TL;DR

This paper introduces CONS, a novel knowledge sharing framework for multi-agent reinforcement learning that allows agents to share both positive and negative insights, improving early exploration and robustness.

Contribution

The paper proposes a new cautious knowledge sharing method that incorporates both positive and negative advice, adaptable over learning stages, without extra training costs.

Findings

CONS outperforms baselines in convergence speed.

CONS achieves higher final performance in complex tasks.

The framework enhances early exploration and robustness.

Abstract

While decentralized training is attractive in multi-agent reinforcement learning (MARL) for its excellent scalability and robustness, its inherent coordination challenges in collaborative tasks result in numerous interactions for agents to learn good policies. To alleviate this problem, action advising methods make experienced agents share their knowledge about what to do, while less experienced agents strictly follow the received advice. However, this method of sharing and utilizing knowledge may hinder the team's exploration of better states, as agents can be unduly influenced by suboptimal or even adverse advice, especially in the early stages of learning. Inspired by the fact that humans can learn not only from the success but also from the failure of others, this paper proposes a novel knowledge sharing framework called Cautiously-Optimistic kNowledge Sharing (CONS). CONS enables each agent to share both positive and negative knowledge and cautiously assimilate knowledge from others, thereby enhancing the efficiency of early-stage exploration and the agents' robustness to adverse advice. Moreover, considering the continuous improvement of policies, agents value negative knowledge more in the early stages of learning and shift their focus to positive knowledge in the later stages. Our framework can be easily integrated into existing Q-learning based methods without introducing additional training costs. We evaluate CONS in several challenging multi-agent tasks and find it excels in environments where optimal behavioral patterns are difficult to discover, surpassing the baselines in terms of convergence rate and final performance.