Discovering Diverse Behaviors via Temporal Contrastive Learning

Faisal Mohamed, Catherine Ji, Benjamin Eysenbach, Glen Berseth

Keywords: reinforcement learning, exploration, intrinsic motivation, surprise, empowerment, contrastive learning

TL;DR: We propose an exploration method based on temporal contrastive representation, our method maximizes state coverage as perceived through the lens of these learned representations.

Abstract: Effective exploration in reinforcement learning requires not only tracking where an agent has been, but also understanding how the agent perceives and represents the world. To learn powerful representations, an agent should actively explore states that contribute to its knowledge of the environment. Temporal representations can capture the information necessary to solve a wide range of potential tasks while avoiding the computational cost associated with full state reconstruction. In this paper, we propose an exploration method that leverages temporal contrastive representations to guide exploration, prioritizing states with unpredictable future outcomes. We demonstrate that such representations can enable the learning of complex exploratory behaviors in locomotion, manipulation, and embodied-AI tasks, revealing capabilities and behaviors that traditionally require extrinsic rewards. Unlike approaches that rely on explicit distance learning or episodic memory mechanisms (e.g., quasimetric-based methods), our method builds directly on temporal similarities, yielding a simpler yet effective strategy for exploration.

Primary Area: reinforcement learning

Submission Number: 11395