Temporal Representations For Exploration: Learning Complex Exploratory Behavior Without Extrinsic Rewards

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-base

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymohamed2026temporal

Related papers

• Time-myopic Go-explore: Learning A State Representation For The Go-explore Paradigm (2023)0.00
• Self-supervised Exploration Via Temporal Inconsistency In Reinforcement Learning (2022)3.58
• A Temporally Correlated Latent Exploration For Reinforcement Learning (2024)0.00
• Long-term Visitation Value For Deep Exploration In Sparse Reward Reinforcement Learning (2020)7.24
• Temporal Difference Uncertainties As A Signal For Exploration (2020)0.00
• Information Content Exploration (2023)0.00
• Directed Exploration In Reinforcement Learning From Linear Temporal Logic (2024)0.00
• Never Give Up: Learning Directed Exploration Strategies (2020)0.00