Overview

State abstraction groups detailed states into simpler representations so agents and models can plan, learn, or act with less memory and data. Approaches include Markov and bisimulation quotients, decision- and task-conditioned representations, causal or topology-aware grouping, learned clustering, and hierarchical abstractions; they are tested in settings such as tabular MDPs, mazes, offline goal-conditioned learning, delayed control, and robotic planning. The central challenge is choosing what to preserve: abstractions that retain full predictive detail may be unnecessarily large, while aggressive compression can hide distinctions that matter for rewards, transitions, or transfer. Current work combines guarantees on value or plan preservation with adaptive and data-driven methods, but reliably balancing compression, decision quality, and generalization remains open.

Latest papers

CardsList

29 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. Structural-Test Geometry as an Inductive Bias for Partially Observable World Models

    Oct 28, 2026Todd Y. ZhouWorld Model LearningLatent World Models

  2. Game-Theoretic Foundations for Undiscounted Bisimulation Metrics

    Oct 28, 2026Matthew Zurek, Yudong Chen, Josiah P. HannaMarkov Decision ProcessesState Abstraction

  3. Prediction Limits and Koopman Closure of Geometry-Induced Soft State Abstractions

    Sep 26, 2026Mohit Kumar, Somayeh KargaranKoopman Operator LearningState Abstraction

  4. Certified Task-Conditioned Active Observability

    Sep 22, 2026Linzhe Zhang, Changming XuActive SensingState Abstraction

  5. What Can a Recurrent State Safely Forget?

    Sep 20, 2026Linzhe Zhang, Changming XuRecurrent Neural NetworksCertified Robustness

  6. An Information-Space Perspective to Scene Graph Sufficiency for Robotic Task Planning

    Sep 14, 2026Başak Sakçak, Francesco VerdojaState AbstractionRobot Task Planning

  7. Windowed A-K-MDP

    Sep 12, 2026Xiangwen Yang, Frankie Cho, Iadine ChadesMarkov Decision ProcessesMarkov Models

  8. Pooling and Drift in Delayed Bandits

    Sep 1, 2026Melika BaghiMulti-Armed BanditsNon-Stationary Bandits

  9. A Data-Driven Approach to State Construction in Markov Models

    Aug 21, 2026Linde Van Gestel, Marie-Anne Guerry, Evy RombautMarkov ModelsState Abstraction

  10. RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States

    Aug 3, 2026Yi Yang, Zhennan Chen, Yihong Zhuang +5State AbstractionState Representation Learning

  11. Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3

    Jul 30, 2026Jens Lehmann, Andrei Aioanei, Sahar VahdatiGame-Playing AgentsAI Coding Agents

  12. Minimal Markovization via Stable Quotients in Holonomy-Cover Decision Processes

    Jul 29, 2026Zuyuan Zhang, Yongshan Chen, Mahdi Imani +1Markov Decision ProcessesPartially Observable RL

  13. Property-driven Causal Abstractions for Markov Decision Processes

    Jul 29, 2026Jule Schmidt, Maximilian Weininger, Clemens Dubslaff +2Markov Decision ProcessesMarkov Models

  14. A Behavioral State Vocabulary in Sony ERS-111 R-CODE

    Jul 13, 2026Christopher A. TuckerRobotic ControlState Abstraction

  15. Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning

    Jun 24, 2026Yivan Zhang, Ziyan Luo, Manuel BaltieriReinforcement LearningState Abstraction

  16. Performance-Driven Environment Abstraction with Multi-Timescale Learning

    Jun 16, 2026Yue Guan, Dipankar Maity, Panagiotis TsiotrasMarkov Decision ProcessesReinforcement Learning

  17. Adaptive state-action abstractions via rate-distortion

    Jun 4, 2026Fernando E. RosasState AbstractionState Representation Learning

  18. Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes

    May 29, 2026Ibne Farabi Shihab, Sanjeda Akter, Anuj SharmaMarkov Decision ProcessesState Abstraction

  19. Answer-Set-Programming-based Abstractions for Reinforcement Learning

    May 29, 2026Rafael Bankosegger, Thomas Eiter, Johannes OetschReinforcement LearningState Abstraction

  20. Abstraction for Offline Goal-Conditioned Reinforcement Learning

    May 21, 2026Clarisse Wibault, Alexander Goldie, Antonio Villares +2Hierarchical RLState Abstraction

  21. Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning

    May 19, 2026Nasehatul Mustakim, Lucas LehnertPartially Observable RLOOD Generalization

  22. Abstract Sim2Real through Approximate Information States

    Apr 16, 2026Yunfu Deng, Yuhao Li, Josiah P. HannaSim-to-Real TransferState Abstraction

  23. Delayed homomorphic reinforcement learning for environments with delayed feedback

    Apr 4, 2026Jongsoo Lee, Jangwon Kim, Soohee HanDelayed RLReinforcement Learning

  24. Multi-level meta-reinforcement learning with skill-based curriculum

    Mar 9, 2026Sichen Yang, Mauro MaggioniReinforcement LearningHierarchical RL

  25. Verification of Unknown Dynamical Systems via Autoencoder Latent Space

    Dec 15, 2025Robert Reed, Luca Laurenti, Morteza LahijanianFormal VerificationState Abstraction