Overview

Successor representations predict which states or features an agent is likely to encounter in the future, allowing value functions to be recomputed when rewards change. Methods include successor features, forward-backward factorization of successor measures, and spectral or low-rank representations, with temporal abstraction and full-gradient training used to improve learning and stability. These representations are tested in control, navigation, visual reinforcement learning, and transfer settings, and are also being explored for hierarchy, safety constraints, and preference learning. A central challenge is balancing compact, reusable representations against errors at long horizons or when rewards and transition dynamics differ from those seen during training.

Latest papers

CardsList

12 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

  1. Robust Successor Features

    Sep 25, 2026Erik Nikulski, Yamen Habib, Vicenç Gomez +3Reinforcement LearningGeneralization in RL

  2. Constrained Reinforcement Learning Using Successor Representations

    Jul 27, 2026Michael Girstl, Alexander Mattick, Christopher MutschlerConstrained RLSafe RL

  3. From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning

    May 31, 2026Jun-Jie Yang, Chia-Heng Hsu, Kui-Yuan Chen +1Pairwise Preference LearningRepresentation Learning

  4. The Terminal Representation in Reinforcement Learning

    May 29, 2026Amir Esterhuysen, Anders JonssonRepresentation Learning for RLTrajectory Representation Learning

  5. Word-Class and Construction-Like Structure Emerges in Neural Successor Representations Trained on Natural Language

    May 23, 2026Mathis Immertreu, Achim Schilling, Thomas Kinfe +1Predictive Representation LearningRepresentation Geometry in Language Models

  6. Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning

    May 13, 2026Stefan Stojanovic, Alexandre ProutiereRepresentation LearningReinforcement Learning

  7. Hierarchical Active Inference using Successor Representations

    Apr 17, 2026Prashant Rangarajan, Rajesh P. N. RaoActive InferenceHierarchical RL

  8. Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning

    Apr 7, 2026Jingbo Sun, Qichao Zhang, Songjun Tu +5Unsupervised RLReinforcement Learning

  9. Full-Gradient Successor Feature Learning for Multi-Task Transfer in Reinforcement Learning

    Apr 1, 2026Ritish Shrirao, Aditya Priyadarshi, Raghuram Bharadwaj DiddigiReinforcement LearningSuccessor Representations

  10. Spectral Alignment in Forward-Backward Representations via Temporal Abstraction

    Mar 20, 2026Seyed Mahdi B. Azad, Jasper Hoffmann, Iman Nematollahi +3Reinforcement LearningRepresentation Learning for RL

  11. Can We Really Learn One Representation to Optimize All Rewards?

    Feb 11, 2026Chongyi Zheng, Royina Karegoudra Jayanth, Benjamin EysenbachZero-Shot RLRepresentation Learning