Saved in:
Bibliographic Details
Main Authors: Zeng, Weihao, Campbell, Joseph, Stepputtis, Simon, Sycara, Katia
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.01377
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911900653060096
author Zeng, Weihao
Campbell, Joseph
Stepputtis, Simon
Sycara, Katia
author_facet Zeng, Weihao
Campbell, Joseph
Stepputtis, Simon
Sycara, Katia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_01377
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Agent Transfer Learning via Temporal Contrastive Learning
Zeng, Weihao
Campbell, Joseph
Stepputtis, Simon
Sycara, Katia
Artificial Intelligence
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.
title Multi-Agent Transfer Learning via Temporal Contrastive Learning
topic Artificial Intelligence
url https://arxiv.org/abs/2406.01377