Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards

TL;DR

This paper introduces a novel exploration method in reinforcement learning that uses temporal contrastive representations to guide exploration, enabling complex behaviors without relying on extrinsic rewards.

Contribution

It proposes a new approach leveraging temporal similarities for exploration, avoiding explicit distance learning or episodic memory mechanisms.

Findings

Enables learning complex behaviors in locomotion, manipulation, and embodied-AI tasks.

Shows effectiveness without relying on extrinsic rewards.

Builds on temporal similarities, simplifying exploration strategies.

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 x 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.