Multi-Agent Transfer Learning via Temporal Contrastive Learning

TL;DR

This paper presents a transfer learning framework for multi-agent reinforcement learning that combines goal-conditioned policies with temporal contrastive learning, improving sample efficiency and interpretability in complex tasks.

Contribution

It introduces a novel approach that automatically discovers sub-goals using temporal contrastive learning, enhancing transfer learning in multi-agent systems.

Findings

Improved sample efficiency, requiring only 21.7% of training samples.

Effective in solving sparse-reward and long-horizon problems.

Enhanced interpretability of multi-agent coordination.

Abstract

This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The approach involves pre-training a goal-conditioned agent, finetuning it on the target domain, and using contrastive learning to construct a planning graph that guides the agent via sub-goals. Experiments on multi-agent coordination Overcooked tasks demonstrate improved sample efficiency, the ability to solve sparse-reward and long-horizon problems, and enhanced interpretability compared to baselines. The results highlight the effectiveness of integrating goal-conditioned policies with unsupervised temporal abstraction learning for complex multi-agent transfer learning. Compared to state-of-the-art baselines, our method achieves the same or better performances while requiring only 21.7% of the training samples.