Year: 2024
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Zeng, Weihao, Campbell, Joseph, Stepputtis, Simon, Sycara, Katia
Institution: Carnegie Mellon University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4399354141