Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards
This addresses the challenge of effective exploration in reinforcement learning for agents, offering a simpler alternative to existing methods like quasimetric-based approaches.
The paper tackles the problem of learning complex exploratory behaviors in reinforcement learning without extrinsic rewards by using temporal contrastive representations to prioritize states with unpredictable future outcomes, demonstrating capabilities in locomotion, manipulation, and embodied-AI tasks.
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.