Representation Learning for RL

RL: Reinforcement Learning

Overview

Representation learning for reinforcement learning studies how agents can turn observations and interaction histories into features that preserve what matters for predicting outcomes and choosing actions. Common approaches include predictive and contrastive latent models, successor and spectral representations, bisimulation metrics, and regularizers that encourage sparse, stable, or disentangled features. These methods support visual control, exploration, offline goal-conditioned navigation, world modeling, and transfer across tasks or environments. A central tension is that reusable features must discard irrelevant variation without losing details needed for control, and better-looking representations do not always improve downstream performance.

Latest papers

CardsList

79 papers10 papers in the last four weeks, down 41% on the four weeks before. 0.1% of all new papers.

  1. Reconstruction vs. Prediction Pre-Training of Discrete Video Representations for Continuous Control

    Nov 18, 2026Ron Kosova, Francesco CroceVideo Representation LearningPredictive Representation Learning

  2. Tensorized Automata: Algebraically Informed Representation Learning for Sequential Decision Making

    Nov 16, 2026Anand Balakrishnan, Dweep Trivedi, Swarat ChaudhuriRepresentation Learning for RLState Representation Learning

  3. Building World Models from Intrinsic Motivation

    Nov 9, 2026Reece Keller, Declan Kutscher, Xaq Pitkow +1Intrinsic MotivationWorld Model Learning

  4. RAIL: Representation-Aligned Imitation Learning for Student-Compatible Teacher Policies

    Nov 9, 2026Meraj Mammadov, Pedro Zuidberg Dos Martires, Johannes Andreas StorkImitation LearningRL for Knowledge Distillation

  5. Permanent and Transient Representations for Continual Reinforcement Learning

    Nov 5, 2026Nishanth Anand, Doina PrecupComplementary Learning SystemsContinual Learning

  6. Provably Efficient Representation Learning for Low-Rank CMDPs

    Nov 5, 2026Kaixuan Liu, Guojun Xiong, Shengpu Tang +2Primal-Dual RLMarkov Decision Processes

  7. On the Feature Evolution of Temporal Difference Learning

    Nov 3, 2026Shangzhe Li, Dechen Zhang, Difan Zou +1Temporal-Difference LearningRepresentation Learning for RL

  8. Decision Transformer with Task-Aware Representations for Offline Meta-Reinforcement Learning

    Nov 2, 2026Xinbo Zhao, Yuhang Liu, Xin Zhang +3Meta-Reinforcement LearningOffline RL

  9. Before We Adapt: The Zero-Shot Generalization Bottleneck in Continual World Models

    Oct 29, 2026Amir Mesbah, Di WuContinual RLWorld Model Learning

  10. Primal-Dual Representation Learning for Low-Rank Constrained MDPs

    Oct 22, 2026Chenhao Zhou, Chao Zhang, Wensong Bai +2Markov Decision ProcessesConstrained RL

  11. Reframing Object-Centric Reinforcement Learning: From Absolute to Relative Representations

    Oct 20, 2026Cedric Derstroff, Jannis Blüml, Janosch Moos +4Object-Centric RLReinforcement Learning

  12. Dynamics-Aligned Representation Learning under Induced Partial Observability

    Oct 18, 2026SM Mazharul Islam, Manfred HuberModel-Based RLRepresentation Learning for RL

  13. Reinforcement Learning with Hawkes-Structured Networks for Market Making

    Oct 12, 2026Fernando Acero, Philipp Plank, Yufei ZhangMarket MakingHawkes Processes

  14. Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning

    Oct 11, 2026Chang-Hoon Jeong, Kisung Shin, Hanwool Sul +1Meta-Reinforcement LearningOOD Generalization

  15. Disentangling Task-Relevant Latent Dynamics for Reward Modeling

    Oct 9, 2026Dayou Li, Jionghao Wang, Peihao Wang +9Dense Reward RLMultimodal Reward Modeling

  16. Q-Shaped Options for Hierarchical Reinforcement Learning

    Oct 8, 2026Clarisse Wibault, Antoine Gorceix, Antonio Léon Villares +5Hierarchical RLRepresentation Learning for RL

  17. FOCUS: From Privileged States to RGB-D with Controlled Modality Switching and Representation Alignment

    Oct 8, 2026Filip Grigorov, Kourosh Darvish, Nandita VijaykumarRobotic RLVisual RL

  18. Taylor Representations for Model-Free RL in Networked MDPs

    Oct 4, 2026Salah Chikhi, Abdelhaq Chaoui, Asuman Ozdaglar +1Markov Decision ProcessesRepresentation Learning for RL

  19. Mastering Atari 2600 Games with Discovered Options

    Oct 2, 2026Erik M. Lintunen, Marlos C. MachadoRL for Game AIHierarchical RL

  20. Learning Transferable Policies from Action-free Time Series Through Dynamical Embeddings

    Oct 2, 2026Niklas Emonds, Georgia KoppeTransfer Learning in RLReinforcement Learning

  21. eRLT: Efficient VLA Reinforcement Learning via Action-Relevant Token Routing

    Oct 1, 2026Dehao Huang, Jianbang Liu, Jianpan Gao +7Efficient VLAsRobotic Manipulation

  22. Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?

    Sep 30, 2026Syed Nazmus Sakib, Abdul Monaf Chowdhury, Nafiul Haque +2Offline RLRepresentation Learning for RL

  23. Reinforcement Learning with Complex (valued) Memories

    Sep 29, 2026Sathya Kamesh Bhethanabhotla, Efstratios Gavves, André BiedenkappPartially Observable RLRecurrent Neural Networks

  24. State Trace Rationale As Auxiliary Task in Reinforcement Learning

    Sep 29, 2026Muhammad U. Nasir, Alex Vogt, Steven D. James +1Reinforcement LearningRepresentation Learning for RL

  25. Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control

    Sep 28, 2026Antonio Pariente, Ignacio Boero, Nikolai Matni +1Dynamical SystemsWorld Model Learning

  26. Offline Policy Evaluation via Mixed Bellman Residuals and Adaptive Critic Representations

    Sep 27, 2026Amitakshar Biswas, Yuhan Li, Ruoqing ZhuOff-Policy EvaluationRepresentation Learning for RL

  27. Self-Confirming Superposition Traps in Reinforcement Learning

    Sep 26, 2026Dai Shi, Andi Han, Feng Chen +3Representation Learning for RL

  28. Learning to Move Cities: Deep Meta-Models and Reinforcement Policies for Calibration and Control in Urban Networks

    Sep 18, 2026Adewumi Augustine Adepitan, Christopher J. Haruna, Oluwasegun Adegoke +2Intelligent Transportation SystemsRL Control