paper-with-me

홈 › Papers

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

2024-06-24 · Vivek Myers, Chongyi Zheng, Anca Dragan, Sergey Levine, Benjamin Eysenbach

Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such temporal distances in stochastic settings have been stymied by an important limitation: these prior approaches do not satisfy the triangle inequality. This is not merely a definitional concern, but translates to an inability to generalize and find shortest paths. In this paper, we build on prior work in contrastive learning and quasimetrics to show how successor features learned by contrastive learning (after a change of variables) form a temporal distance that does satisfy the triangle inequality, even in stochastic settings. Importantly, this temporal distance is computationally efficient to estimate, even in high-dimensional and stochastic settings. Experiments in controlled settings and benchmark suites demonstrate that an RL algorithm based on these new temporal distances exhibits combinatorial generalization (i.e., "stitching") and can sometimes learn more quickly than prior methods, including those based on quasimetrics.

📄 PDF Abstract BibTeX arXiv:2406.17098

Code (1)

vivekmyers/contrastive_metrics 공식 구현 jax

Tasks

Contrastive LearningDecision Making

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations

2025-09-24 · Vivek Myers, Bill Chunyuan Zheng, Benjamin Eysenbach, Sergey Levine arxiv

Approaches for goal-conditioned reinforcement learning (GCRL) often use learned state representations to extract goal-reaching policies. Two frameworks for representation structure have yielded particularly effective GCR…

Representation LearningReinforcement LearningContrastive Learning

Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning

2024-12-11 · Chongyi Zheng, Jens Tuyls, Joanne Peng, Benjamin Eysenbach

Self-supervised learning has the potential of lifting several of the key challenges in reinforcement learning today, such as exploration, representation learning, and reward design. Recent work (METRA) has effectively ar…

Representation LearningSelf-Supervised Learning

Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning

2025-06-11 · Daniel Lawson, Adriana Hugessen, Charlotte Cloutier, Glen Berseth 외

Behavioral cloning (BC) methods trained with supervised learning (SL) are an effective way to learn policies from human demonstrations in domains like robotics. Goal-conditioning these policies enables a single generalis…

Representation Learning

Full-Gradient Successor Feature Representations

2026-04-01 · Ritish Shrirao, Aditya Priyadarshi, Raghuram Bharadwaj Diddigi arxiv

Successor Features (SF) combined with Generalized Policy Improvement (GPI) provide a robust framework for transfer learning in Reinforcement Learning (RL) by decoupling environment dynamics from reward functions. However…

Reinforcement LearningTransfer Learning

Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning

2017-07-31 · Lucas Lehnert, Stefanie Tellex, Michael L. Littman

One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)