Learning to Share in Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2112.08702v1
• Date: Thu, 16 Dec 2021 08:43:20 GMT
• Title: Learning to Share in Multi-Agent Reinforcement Learning
• Authors: Yuxuan Yi, Ge Li, Yaowei Wang, Zongqing Lu
• Abstract summary: We study the problem of networked multi-agent reinforcement learning (MARL) Inspired by the fact that textitsharing plays a key role in human's learning of cooperation, we propose LToS. For each agent, the high-level policy learns how to share reward with neighbors to decompose the global objective, while the low-level policy learns to optimize local objective induced by the high-level policies in the neighborhood.
• Score: 33.462384381980065
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we study the problem of networked multi-agent reinforcement learning (MARL), where a number of agents are deployed as a partially connected network and each interacts only with nearby agents. Networked MARL requires all agents make decision in a decentralized manner to optimize a global objective with restricted communication between neighbors over the network. Inspired by the fact that \textit{sharing} plays a key role in human's learning of cooperation, we propose LToS, a hierarchically decentralized MARL framework that enables agents to learn to dynamically share reward with neighbors so as to encourage agents to cooperate on the global objective. For each agent, the high-level policy learns how to share reward with neighbors to decompose the global objective, while the low-level policy learns to optimize local objective induced by the high-level policies in the neighborhood. The two policies form a bi-level optimization and learn alternately. We empirically demonstrate that LToS outperforms existing methods in both social dilemma and networked MARL scenario.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.