{"total":66,"rows":[{"id":"2206.10680","title":"Learning Neuro-Symbolic Skills for Bilevel Planning","created":"2022-06-21","cited_by_count":58,"area":null},{"id":"2203.09634","title":"Predicate Invention for Bilevel Planning","created":"2022-03-17","cited_by_count":49,"area":null},{"id":"2106.04379","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":44,"area":null},{"id":"2105.12272","title":"Provable Representation Learning for Imitation with Contrastive Fourier Features","created":"2021-05-26","cited_by_count":34,"area":"offlinerl"},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29,"area":null},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2102.01514","title":"Metrics and continuity in reinforcement learning","created":"2021-02-02","cited_by_count":26,"area":null},{"id":"2503.00361","title":"Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding","created":"2025-03-01","cited_by_count":24,"area":"mllm"},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2304.12000","title":"Hierarchical State Abstraction Based on Structural Information Principles","created":"2023-04-24","cited_by_count":14,"area":null},{"id":"2106.11935","title":"Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL","created":"2021-06-22","cited_by_count":12,"area":"offlinerl"},{"id":"2202.02881","title":"Approximate Policy Iteration with Bisimulation Metrics","created":"2022-02-06","cited_by_count":12,"area":null},{"id":"2402.18759","title":"Learning with Language-Guided State Abstractions","created":"2024-02-28","cited_by_count":11,"area":"offlinerl"},{"id":"2501.00296","title":"From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models","created":"2024-12-31","cited_by_count":11,"area":"wm"},{"id":"2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2406.02696","title":"iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning","created":"2024-06-04","cited_by_count":9,"area":"deeprl"},{"id":"2505.13346","title":"J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization","created":"2025-05-19","cited_by_count":9,"area":"lr"},{"id":"2303.04912","title":"Embodied Active Learning of Relational State Abstractions for Bilevel Planning","created":"2023-03-08","cited_by_count":8,"area":null},{"id":"2406.16249","title":"An Optimal Tightness Bound for the Simulation Lemma","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2307.14316","title":"Reinforcement Learning by Guided Safe Exploration","created":"2023-07-26","cited_by_count":7,"area":null},{"id":"2403.16369","title":"Learning Action-based Representations Using Invariance","created":"2024-03-25","cited_by_count":7,"area":"deeprl"},{"id":"2605.10870","title":"Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2210.01426","title":"Continuous Monte Carlo Graph Search","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4,"area":null},{"id":"2406.15850","title":"Learning Abstract World Model for Value-preserving Planning with Options","created":"2024-06-22","cited_by_count":4,"area":"wm"},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2510.06540","title":"Scalable Policy-Based RL Algorithms for POMDPs","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2112.13141","title":"On the Unreasonable Efficiency of State Space Clustering in Personalization Tasks","created":"2021-12-24","cited_by_count":3,"area":null},{"id":"2209.07696","title":"Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes","created":"2022-09-16","cited_by_count":3,"area":null},{"id":"2310.06513","title":"Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction","created":"2023-10-10","cited_by_count":3,"area":null},{"id":"2603.21399","title":"The Myhill-Nerode Theorem for Bounded Interaction: Canonical Abstractions via Agent-Bounded Indistinguishability","created":"2026-03-22","cited_by_count":3,"area":null},{"id":"2107.06405","title":"Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks","created":"2021-07-13","cited_by_count":2,"area":null},{"id":"2107.11053","title":"An Adaptive State Aggregation Algorithm for Markov Decision Processes","created":"2021-07-23","cited_by_count":2,"area":null},{"id":"2208.14407","title":"An Analysis of Model-Based Reinforcement Learning From Abstracted Observations","created":"2022-08-30","cited_by_count":2,"area":null},{"id":"2303.00516","title":"Exploiting Multiple Abstractions in Episodic RL via Reward Shaping","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2605.14304","title":"Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry","created":"2026-05-14","cited_by_count":2,"area":"deeprl"},{"id":"2102.08307","title":"Dynamic neighbourhood optimisation for task allocation using multi-agent","created":"2021-02-16","cited_by_count":1,"area":null},{"id":"2110.09196","title":"Option Transfer and SMDP Abstraction with Successor Features","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2203.08019","title":"Optimal Admission Control for Multiclass Queues with Time-Varying Arrival Rates via State Abstraction","created":"2022-03-14","cited_by_count":1,"area":null},{"id":"2304.03773","title":"Safe Explicable Planning","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2306.12981","title":"Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2402.08813","title":"Model approximation in MDPs with unbounded per-step cost","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2407.15820","title":"On shallow planning under partial observability","created":"2024-07-22","cited_by_count":1,"area":"deeprl"},{"id":"2505.19837","title":"Multi-Agent Reinforcement Learning in Cybersecurity: From Fundamentals to Applications","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2603.06813","title":"Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2604.04808","title":"Selecting Decision-Relevant Concepts in Reinforcement Learning","created":"2026-04-06","cited_by_count":1,"area":"deeprl"},{"id":"2609.02322","title":"What Is Worth Representing? Representational Empowerment for Continual Model Construction","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2110.04664","title":"Using Human-Guided Causal Knowledge for More Generalized Robot Task Planning","created":"2021-10-09","cited_by_count":0,"area":null},{"id":"2112.13386","title":"Reducing Planning Complexity of General Reinforcement Learning with Non-Markovian Abstractions","created":"2021-12-26","cited_by_count":0,"area":null},{"id":"2210.01955","title":"Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2302.06009","title":"Policy-Induced Self-Supervision Improves Representation Finetuning in Visual RL","created":"2023-02-12","cited_by_count":0,"area":null},{"id":"2412.15877","title":"Approximate State Abstraction for Markov Games","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2510.09965","title":"Homomorphic Mappings for Value-Preserving State Aggregation in Markov Decision Processes","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2511.22104","title":"Representative Action Selection for Large Action Space: From Bandits to MDPs","created":"2025-11-27","cited_by_count":0,"area":"deeprl"},{"id":"2601.20985","title":"Distributional Active Inference","created":"2026-01-28","cited_by_count":0,"area":"deeprl"},{"id":"2605.15975","title":"Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning","created":"2026-05-15","cited_by_count":0,"area":"wm"},{"id":"2605.20272","title":"Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning","created":"2026-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2606.06123","title":"Adaptive state-action abstractions via rate-distortion","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.25357","title":"Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning","created":"2026-06-24","cited_by_count":0,"area":"deeprl"},{"id":"2608.06762","title":"Sub-Quadratic Bisimulation Metrics via Approximate Nearest Neighbors: Coverage-Augmented Guarantees and Computable Two-Sided Certificates","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.20428","title":"Approximate Homomorphisms and Convergent Representations in Transducers","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.13676","title":"Windowed A-K-MDP","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.38890","title":"PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.12135","title":"Q-Shaped Options for Hierarchical Reinforcement Learning","created":"2026-10-08","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}