Dual Goal Representations

Abstract

In this work, we introduce dual goal representations for goal-conditioned reinforcement learning (GCRL). A dual goal representation characterizes a state by "the set of temporal distances from all other states"; in other words, it encodes a state through its relations to every other state, measured by temporal distance. This representation provides several appealing theoretical properties. First, it depends only on the intrinsic dynamics of the environment and is invariant to the original state representation. Second, it contains provably sufficient information to recover an optimal goal-reaching policy, while being able to filter out exogenous noise. Based on this concept, we develop a practical goal representation learning method that can be combined with any existing GCRL algorithm. Through diverse experiments on the OGBench task suite, we empirically show that dual goal representations consistently improve offline goal-reaching performance across 20 state- and pixel-based tasks.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypark2025dual

Related papers

• Contrastive Learning As Goal-conditioned Reinforcement Learning (2022)0.00
• Provably Efficient Offline Goal-conditioned Reinforcement Learning With General Function Approximation And Single-policy Concentrability (2023)0.00
• Goal Reaching With Eikonal-constrained Hierarchical Quasimetric Reinforcement Learning (2025)0.00
• Imagine Beyond! Distributionally Robust Auto-encoding For State Space Coverage In Online Reinforcement Learning (2025)0.00
• Variational Empowerment As Representation Learning For Goal-based Reinforcement Learning (2021)0.00
• SMORE: Score Models For Offline Goal-conditioned Reinforcement Learning (2023)0.00
• Reconciling Spatial And Temporal Abstractions For Goal Representation (2024)1.69
• Dual RL: Unification And New Methods For Reinforcement And Imitation Learning (2023)0.00