{"total":133,"rows":[{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458,"area":"wm"},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170,"area":"wm"},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123,"area":null},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121,"area":null},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108,"area":null},{"id":"2206.15477","title":"Denoised MDPs: Learning World Models Better Than the World Itself","created":"2022-06-30","cited_by_count":68,"area":"wm"},{"id":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52,"area":null},{"id":"2110.14096","title":"Towards Robust Bisimulation Metric Learning","created":"2021-10-27","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":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"area":null},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42,"area":null},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2204.13060","title":"Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning","created":"2022-04-27","cited_by_count":38,"area":null},{"id":"2102.10960","title":"Return-Based Contrastive Representation Learning for Reinforcement Learning","created":"2021-02-22","cited_by_count":36,"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":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33,"area":null},{"id":"2110.05721","title":"Action-Sufficient State Representation Learning for Control with Structural Constraints","created":"2021-10-12","cited_by_count":31,"area":null},{"id":"2103.01948","title":"Offline Reinforcement Learning with Pseudometric Learning","created":"2021-03-02","cited_by_count":28,"area":"offlinerl"},{"id":"2210.10195","title":"Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation","created":"2022-10-18","cited_by_count":28,"area":null},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2602.02454","title":"World-Gymnast: Training Robots with Reinforcement Learning in a World Model","created":"2026-02-02","cited_by_count":27,"area":"wm"},{"id":"2102.01514","title":"Metrics and continuity in reinforcement learning","created":"2021-02-02","cited_by_count":26,"area":null},{"id":"2111.03189","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2111.07775","title":"Learning Representations for Pixel-based Control: What Matters and Why?","created":"2021-11-15","cited_by_count":24,"area":null},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2306.06561","title":"Learning World Models with Identifiable Factorization","created":"2023-06-11","cited_by_count":23,"area":"wm"},{"id":"2405.06263","title":"Learning Latent Dynamic Robust Representations for World Models","created":"2024-05-10","cited_by_count":21,"area":"wm"},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20,"area":null},{"id":"2106.02193","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2606.20104","title":"Sensorimotor World Models: Perception for Action via Inverse Dynamics","created":"2026-06-18","cited_by_count":20,"area":"wm"},{"id":"2201.00248","title":"Transfer RL across Observation Feature Spaces via Model-Based Regularization","created":"2022-01-01","cited_by_count":18,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2111.14629","title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions","created":"2021-11-29","cited_by_count":17,"area":"offlinerl"},{"id":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2510.06714","title":"Dual Goal Representations","created":"2025-10-08","cited_by_count":16,"area":"deeprl"},{"id":"2205.10218","title":"Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions","created":"2022-05-20","cited_by_count":15,"area":null},{"id":"2211.11603","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","created":"2022-11-21","cited_by_count":15,"area":"offlinerl"},{"id":"2112.15303","title":"SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning","created":"2021-12-31","cited_by_count":14,"area":null},{"id":"2302.12003","title":"Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions","created":"2023-02-12","cited_by_count":14,"area":null},{"id":"2210.15206","title":"Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision","created":"2022-10-27","cited_by_count":13,"area":"synth"},{"id":"2401.00298","title":"Principal-Agent Reward Shaping in MDPs","created":"2023-12-30","cited_by_count":13,"area":null},{"id":"2602.18639","title":"Learning Invariant Visual Representations for Planning with Joint-Embedding Predictive World Models","created":"2026-02-20","cited_by_count":13,"area":"wm"},{"id":"2112.02807","title":"MDPFuzz: Testing Models Solving Markov Decision Processes","created":"2021-12-06","cited_by_count":12,"area":null},{"id":"2202.02881","title":"Approximate Policy Iteration with Bisimulation Metrics","created":"2022-02-06","cited_by_count":12,"area":null},{"id":"2111.00213","title":"Adjacency constraint for efficient hierarchical reinforcement learning","created":"2021-10-30","cited_by_count":10,"area":null},{"id":"2204.12026","title":"BATS: Best Action Trajectory Stitching","created":"2022-04-26","cited_by_count":10,"area":"offlinerl"},{"id":"2306.02419","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","created":"2023-06-04","cited_by_count":10,"area":null},{"id":"2310.17139","title":"Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning","created":"2023-10-26","cited_by_count":10,"area":"offlinerl"},{"id":"2212.04280","title":"Model-based trajectory stitching for improved behavioural cloning and its applications","created":"2022-12-08","cited_by_count":9,"area":"offlinerl"},{"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":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2503.06343","title":"Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning","created":"2025-03-08","cited_by_count":8,"area":"deeprl"},{"id":"2212.07486","title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","created":"2022-12-14","cited_by_count":7,"area":null},{"id":"2310.20663","title":"Offline RL with Observation Histories: Analyzing and Improving Sample Complexity","created":"2023-10-31","cited_by_count":7,"area":"offlinerl"},{"id":"2403.16369","title":"Learning Action-based Representations Using Invariance","created":"2024-03-25","cited_by_count":7,"area":"deeprl"},{"id":"2103.04706","title":"A Taxonomy of Similarity Metrics for Markov Decision Processes","created":"2021-03-08","cited_by_count":6,"area":null},{"id":"2107.01348","title":"Examining average and discounted reward optimality criteria in reinforcement learning","created":"2021-07-03","cited_by_count":6,"area":null},{"id":"2306.14133","title":"Provably Convergent Policy Optimization via Metric-aware Trust Region Methods","created":"2023-06-25","cited_by_count":6,"area":null},{"id":"2406.04056","title":"Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently","created":"2024-06-06","cited_by_count":6,"area":null},{"id":"2410.04553","title":"Bisimulation metric for Model Predictive Control","created":"2024-10-06","cited_by_count":6,"area":"deeprl"},{"id":"2503.05042","title":"Provably Correct Automata Embeddings for Optimal Automata-Conditioned Reinforcement Learning","created":"2025-03-06","cited_by_count":6,"area":"deeprl"},{"id":"2303.01668","title":"RePreM: Representation Pre-training with Masked Model for Reinforcement Learning","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2602.19373","title":"Stable Deep Reinforcement Learning via Isotropic Gaussian Representations","created":"2026-02-22","cited_by_count":5,"area":"deeprl"},{"id":"2212.13088","title":"Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities","created":"2022-12-26","cited_by_count":4,"area":null},{"id":"2310.18409","title":"State-Action Similarity-Based Representations for Off-Policy Evaluation","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2505.16217","title":"Reward-Aware Proto-Representations in Reinforcement Learning","created":"2025-05-22","cited_by_count":4,"area":"deeprl"},{"id":"2509.18714","title":"A Generalized Bisimulation Metric of State Similarity between Markov Decision Processes: From Theoretical Propositions to Applications","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2201.12300","title":"Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulation","created":"2022-01-28","cited_by_count":3,"area":null},{"id":"2310.19804","title":"A Kernel Perspective on Behavioural Metrics for Markov Decision Processes","created":"2023-10-05","cited_by_count":3,"area":null},{"id":"2402.10820","title":"Goal-Conditioned Reinforcement Learning from Sub-Optimal Data on Metric Spaces","created":"2024-02-16","cited_by_count":3,"area":"offlinerl"},{"id":"2411.06174","title":"State Chrono Representation for Enhancing Generalization in Reinforcement Learning","created":"2024-11-09","cited_by_count":3,"area":"deeprl"},{"id":"2507.18519","title":"Revisiting Bisimulation Metric for Robust Representations in Reinforcement Learning","created":"2025-07-24","cited_by_count":3,"area":"deeprl"},{"id":"2510.02287","title":"MultiModal Action Conditioned Video Generation","created":"2025-10-02","cited_by_count":3,"area":"wm"},{"id":"2510.12312","title":"Deep SPI: Safe Policy Improvement via World Models","created":"2025-10-14","cited_by_count":3,"area":"wm"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2605.01694","title":"Latent State Design for World Models under Sufficiency Constraints","created":"2026-05-03","cited_by_count":3,"area":"wm"},{"id":"2107.06405","title":"Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks","created":"2021-07-13","cited_by_count":2,"area":null},{"id":"2111.10297","title":"Expert-Guided Symmetry Detection in Markov Decision Processes","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2402.00807","title":"Augmenting Offline Reinforcement Learning with State-only Interactions","created":"2024-02-01","cited_by_count":2,"area":"offlinerl"},{"id":"2404.17687","title":"Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Review","created":"2024-04-26","cited_by_count":2,"area":"deeprl"},{"id":"2410.00704","title":"Contrastive Abstraction for Reinforcement Learning","created":"2024-10-01","cited_by_count":2,"area":"deeprl"},{"id":"2505.18005","title":"Distances for Markov chains from sample streams","created":"2025-05-23","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":"2607.04409","title":"Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling","created":"2026-07-05","cited_by_count":2,"area":"wm"},{"id":"2211.16315","title":"Learning and Understanding a Disentangled Feature Representation for Hidden Parameters in Reinforcement Learning","created":"2022-11-29","cited_by_count":1,"area":"wm"},{"id":"2405.14374","title":"State-Constrained Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":1,"area":"offlinerl"},{"id":"2412.17123","title":"Fairness in Reinforcement Learning with Bisimulation Metrics","created":"2024-12-22","cited_by_count":1,"area":"deeprl"},{"id":"2502.01316","title":"Learning Fused State Representations for Control from Multi-View Observations","created":"2025-02-03","cited_by_count":1,"area":"deeprl"},{"id":"2506.12254","title":"Lower Bound on Howard Policy Iteration for Deterministic Markov Decision Processes","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2506.21129","title":"Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments","created":"2025-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2602.18724","title":"Task-Aware Exploration via a Predictive Bisimulation Metric","created":"2026-02-21","cited_by_count":1,"area":"deeprl"},{"id":"2605.09364","title":"MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","created":"2026-05-10","cited_by_count":1,"area":"deeprl"},{"id":"2605.20609","title":"Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"offlinerl"},{"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":"2204.04324","title":"Approximate discounting-free policy evaluation from transient and recurrent states","created":"2022-04-08","cited_by_count":0,"area":null},{"id":"2207.13813","title":"Structural Similarity for Improved Transfer in Reinforcement Learning","created":"2022-07-27","cited_by_count":0,"area":null},{"id":"2209.05333","title":"Rollout Total Correlation for Deep Reinforcement Learning","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2209.06827","title":"Weakly Supervised Invariant Representation Learning Via Disentangling Known and Unknown Nuisance Factors","created":"2022-09-15","cited_by_count":0,"area":null}],"next_cursor":"100"}