State Representation Learning

Follow this topic Ask about this topic

State representation learning asks how an agent or model can turn observations and histories into an internal state that preserves what matters for future prediction or action. Methods include predictive objectives such as JEPA and successor representations, inverse-dynamics and bisimulation learning, recurrent belief states, and task- or reward-driven abstractions. They are studied in partially observed control, pixel-based robot planning, navigation, and dynamical-system forecasting, where useful states can improve sample efficiency, transfer, and robustness. A central tension is that predictive accuracy or reconstruction does not guarantee a decision-sufficient state: representations must retain control-relevant distinctions without carrying irrelevant detail, and their adequacy remains difficult to measure.

Latest papers

126 papers22 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation
May 13, 2026Maxime Alvarez, Ryo Watanabe, Paul Crook +4Robot Policy Learning Generalization in Robotic Manipulation
TELEXISTENCE Inc, Foundation Model Division, Japan. · The University of Tokyo, Japan.
WriteSAE: Sparse Autoencoders for Recurrent State
May 12, 2026Jack YoungRecurrent Language Models Language Model Steering
Indiana University
Policy Gradient Methods for Non-Markovian Reinforcement Learning
May 11, 2026Avik Kar, Siddharth Chandak, Rahul Singh +4Reinforcement Learning Policy Gradient Methods
Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India. · Department of Electrical Engineering, Stanford University, Stanford, CA, USA. · Department of Electrical and Electronics Engineering, Nanyang Technological University, Singapore. +1
MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning
May 10, 2026Valliappan Chidambaram Adaikkappan, Sai Rajeswar, Pietro Mazzaglia +1Offline RL Predictive Representation Learning
Mila, McGill University · Qualcomm Research
From Causal Graphs to Markovian States: Multi-Order State Exposure for Deep RL
May 8, 2026Jiamin Xu, Jacqueline Maasch, Kyra GanMarkov Decision Processes Causal Representation Learning
Cornell Tech, New York, NY
Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies
May 7, 2026Magnus Victor Boock, Abdullah Akgül, Mustafa Mert Çelikok +1Sequential Decision Making Offline RL
Department of Mathematics and Computer Science University of Southern Denmark
Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics
May 7, 2026Likhita Yerra, Remi Uttejitha AllamExplainable Artificial Intelligence Quantitative Finance
AIVANCITY School of AI and Data · AIVANCITY School of AI & Data
Modular Reinforcement Learning For Cooperative Swarms
May 6, 2026Erel Shtossel, Gal A. KaminkaMulti-Robot Systems Reinforcement Learning
Bar Ilan University Ramat Gan, Israel
Latent State Design for World Models under Sufficiency Constraints
May 3, 2026Keon Woo KimRepresentation Learning Predictive Representation Learning
Om Labs
Lost in State Space: Probing Frozen Mamba Representations
Apr 30, 2026Bhagyashree Wagh, Akash SinghRepresentation Geometry Representation Collapse
University of Washington · University of Florida
The Bandit's Blind Spot: The Critical Role of User State Representation in Recommender Systems
Apr 29, 2026Pedro R. Pires, Gregorio F. Azevedo, Rafael T. Sereicikas +2User Modeling Recommender Systems
Federal University of São Carlos Sorocaba, São Paulo, Brazil
State Beyond Appearance: Diagnosing and Improving State Consistency in Dial-Based Measurement Reading
Apr 29, 2026Yuanze Hu, Gen Li, Yuqin Lan +5Multimodal Robustness Cross-Modal Alignment
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, China · Beihang University, Beijing, China · Fudan University, Shanghai, China +1
Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data
Apr 27, 2026K. Michael Martini, Eslam Abdelaleem, Paarth Gulati +1Dynamical Systems Information Bottleneck
Department of Physics, Emory University, Atlanta, GA, USA · Schools of Physics and Psychology, Georgia Institute of Technology, Atlanta, GA, USA · Initiative in Theory and Modeling of Living Systems, Emory University, Atlanta, GA, USA +1
Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness
Apr 23, 2026Zihan Liang, Ziwen Pan, Ruoxuan XiongClinical Outcome Prediction Offline RL
Emory University, Atlanta, USA
Self-Predictive Representation for Autonomous UAV Object-Goal Navigation
Apr 22, 2026Angel Ayala, Donling Sui, Francisco Cruz +3UAV Navigation Predictive Representation Learning
Escola Polit´ecnica de Pernambuco, Universidade de Pernambuco, Recife, Brasil · School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, Australia · Escuela de Ingenier´ıa, Universidad Central de Chile, Santiago, Chile
Hierarchical Active Inference using Successor Representations
Apr 17, 2026Prashant Rangarajan, Rajesh P. N. RaoActive Inference Hierarchical RL
Paul G. Allen Center for Computer Science and Engineering, University of Washington, Seattle, USA
Predictive Representations for Skill Transfer in Reinforcement Learning
Apr 8, 2026Ruben Vereecken, Luke Dickens, Alessandra RussoTransfer Learning in RL Predictive State Representations
Computer Science, Imperial College, UK · Information Studies, UCL, UK
Derived Fields Increase the Recoverable Information in Budgeted Neural PDE Surrogate
Mar 31, 2026Wenshuo Wang, Fan ZhangPDE Surrogate Modeling Neural Surrogate Modeling
School of Future Technology, South China University of Technology, China · State Key Laboratory of Ocean Sensing & Ocean College, Zhejiang University, China · Kavli Institute for Astrophysics and Space Research, Massachusetts Institute of Technology, USA
GLU: Global-Local-Uncertainty Fusion for Scalable Spatiotemporal Reconstruction and Forecasting
Mar 27, 2026Linzheng Wang, Jason Chen, Nicolas Tricard +2Spatiotemporal Forecasting Digital Twins
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, 02139, MA, United States of America.
Behavioral Heterogeneity as Quantum-Inspired Representation
Mar 24, 2026Mohammad Elayan, Wissam KontarState Representation Learning Latent Dynamics Modeling
University of Nebraska–Lincoln, Lincoln, NE, USA
Generalizing Dynamics Modeling More Easily from Representation Perspective
Mar 24, 2026Yiming Wang, Zhengnan Zhang, Genghe Zhang +7Dynamical Systems Latent Dynamics Modeling
College of Computer Science and Technology, and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, China · College of Software and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, China · School of Computing, Belfast, Northern Ireland, UK +1
RuntimeSlicer: Towards Generalizable Unified Runtime State Representation for Failure Management
Mar 23, 2026Lingzhe Zhang, Tong Jia, Weijie Hong +9State Representation Learning Multimodal Pretraining
Peking University, Beijing, China · Huawei Technologies Co., Ltd., Beijing, China · Huawei Technologies Co., Ltd., Hong Kong SAR, China +1
Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
Mar 16, 2026Pranaya Jajoo, Harshit Sikchi, Siddhant Agarwal +3Behavioral Foundation Models Zero-Shot RL
Department of Computing Science, University of Alberta, Canada · Alberta Machine Intelligence Institute (Amii) · The University of Texas at Austin +2
Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition
Mar 14, 2026Seokmin Lee, Yunghee Lee, Byeonghyun Pak +1State Representation Learning Self-Supervised Visual Representation Learning
Agency for Defense Development
Few-Shot Adaptation to Non-Stationary Environments via Latent Trend Embedding for Robotics
Mar 11, 2026Yasuyuki Fujii, Emika Kameda, Hiroki Fukada +3Robot Policy Adaptation Few-Shot Domain Adaptation
College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan · College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan. · Production and Technology Department, NIPPN CORPORATION, Tokyo, Japan +5
Reward Prediction with Factorized World States
Mar 10, 2026Yijun Shen, Delong Chen, Xianming Hu +4Reward Modeling State Representation Learning
East China Normal University · HKUST
Impact of Connectivity on Laplacian Representations in Reinforcement Learning
Mar 9, 2026Tommaso Giorgi, Pierriccardo Olivieri, Keyue Jiang +2Reinforcement Learning Representation Learning for RL
Baker Hughes, Florence, Italy · Politecnico di Milano · University College London, AI Center (UCL) +1
Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II
Mar 8, 2026Yi Tian, Kaiqing Zhang, Russ Tedrake +1Linear Quadratic Regulator State Representation Learning
Massachusetts Institute of Technology · University of Maryland, College Park · Technical University Munich
RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States
Mar 7, 2026Xiangjie Xiao, Cong Zhang, Wen Song +1Flexible Job Shop Scheduling Job Shop Scheduling
School of Computing and Information Systems, Singapore Management University, Singapore · College of Computing and Data Science, Nanyang Technological University, Singapore · Institute of Marine Science and Technology, Shandong University, China
On Sample-Efficient Generalized Planning via Learned Transition Models
Feb 26, 2026Nitin Gupta, Vishal Pallagani, John A. Aydin +1Model-Based Planning OOD Generalization
University of South Carolina

May 13, 2026J/K move · Enter open · S save

When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation

Maxime Alvarez, Ryo Watanabe, Paul Crook, Afshin Zeinaddini Meymand+3

TELEXISTENCE Inc, Foundation Model Division, Japan. · The University of Tokyo, Japan.

Robot Policy Learning Generalization in Robotic Manipulation Robotic Manipulation State Representation Learning Robot Policy Generalization

Open paper AskPDF arXiv

As end-to-end robotic policies are progressively deployed in the real world to solve real tasks, they face a gap between the training and inference conditions. Scaling the amount and diversity of the training data has shown some success in improving zero-shot generalization, yet robots still fail when faced with new, unseen test conditions. For instance, while robots with fixed frames of reference are common, those with moving frames pose a greater challenge for deployment. To address this specific instance of the issue, we present a study of strategies for encoding the robot's proprioceptive state to improve both in- and out-of-distribution performance at test time. Through a systematic study of joint representations, we find that a simple episode-wise relative frame provides the best trade-off between task performance and robustness, outperforming the baselines in extensive real-robot experiments conducted in a realistic test environment. The results suggest a practical path to leveraging data collected by robots with varying frames of reference and deployment to unseen test configurations.