{"total":58,"rows":[{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121,"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":"2206.13452","title":"Causal Dynamics Learning for Task-Independent State Abstraction","created":"2022-06-27","cited_by_count":65,"area":null},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2207.08229","title":"Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models","created":"2022-07-17","cited_by_count":45,"area":null},{"id":"2502.00379","title":"Latent Action Learning Requires Supervision in the Presence of Distractors","created":"2025-02-01","cited_by_count":44,"area":null},{"id":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34,"area":null},{"id":"2305.16985","title":"Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation","created":"2023-05-26","cited_by_count":31,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2307.02064","title":"Facing Off World Model Backbones: RNNs, Transformers, and S4","created":"2023-07-05","cited_by_count":31,"area":"wm"},{"id":"2204.08585","title":"INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"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":"2306.06561","title":"Learning World Models with Identifiable Factorization","created":"2023-06-11","cited_by_count":23,"area":"wm"},{"id":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21,"area":null},{"id":"2405.06263","title":"Learning Latent Dynamic Robust Representations for World Models","created":"2024-05-10","cited_by_count":21,"area":"wm"},{"id":"2309.00082","title":"RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability","created":"2023-08-31","cited_by_count":18,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"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":"2312.17116","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","created":"2023-12-28","cited_by_count":12,"area":null},{"id":"2204.11827","title":"Task-Induced Representation Learning","created":"2022-04-25","cited_by_count":11,"area":null},{"id":"2401.12497","title":"Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning","created":"2024-01-23","cited_by_count":11,"area":"deeprl"},{"id":"2303.06121","title":"Ignorance is Bliss: Robust Control via Information Gating","created":"2023-03-10","cited_by_count":10,"area":null},{"id":"2306.10695","title":"SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models","created":"2023-06-19","cited_by_count":10,"area":"offlinerl"},{"id":"2403.09976","title":"AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors","created":"2024-03-15","cited_by_count":10,"area":"wm"},{"id":"2302.05342","title":"Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL","created":"2023-02-10","cited_by_count":9,"area":null},{"id":"2410.10834","title":"Focus On What Matters: Separated Models For Visual-Based RL Generalization","created":"2024-09-29","cited_by_count":6,"area":"deeprl"},{"id":"2412.05766","title":"Policy-shaped prediction: avoiding distractions in model-based reinforcement learning","created":"2024-12-08","cited_by_count":6,"area":"deeprl"},{"id":"2506.16565","title":"Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control","created":"2025-06-19","cited_by_count":6,"area":"wm"},{"id":"2303.05092","title":"Task Aware Dreamer for Task Generalization in Reinforcement Learning","created":"2023-03-09","cited_by_count":5,"area":"wm"},{"id":"2410.09972","title":"Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions","created":"2024-10-13","cited_by_count":5,"area":"deeprl"},{"id":"2310.00229","title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2607.26924","title":"Temporally Centered SIGReg Improves LeWorldModel Representations for Robot Policy Learning","created":"2026-07-29","cited_by_count":4,"area":"wm"},{"id":"2212.14511","title":"Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part I","created":"2022-12-30","cited_by_count":3,"area":null},{"id":"2309.12628","title":"Sequential Action-Induced Invariant Representation for Reinforcement Learning","created":"2023-09-22","cited_by_count":3,"area":null},{"id":"2407.10967","title":"BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning","created":"2024-07-15","cited_by_count":3,"area":"offlinerl"},{"id":"2412.12870","title":"Physically Interpretable World Models via Weakly Supervised Representation Learning","created":"2024-12-17","cited_by_count":3,"area":"wm"},{"id":"2607.18715","title":"DWM: Separating World Effects from Actions in Latent World Models","created":"2026-07-21","cited_by_count":3,"area":"wm"},{"id":"2608.12939","title":"Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency","created":"2026-08-13","cited_by_count":3,"area":"wm"},{"id":"2211.00086","title":"Disentangled (Un)Controllable Features","created":"2022-10-31","cited_by_count":2,"area":null},{"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":"2608.06706","title":"Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection","created":"2026-08-07","cited_by_count":2,"area":"wm"},{"id":"2401.09258","title":"Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2406.09486","title":"SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets","created":"2024-06-13","cited_by_count":1,"area":"offlinerl"},{"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":"2502.09923","title":"Self-Consistent Model-based Adaptation for Visual Reinforcement Learning","created":"2025-02-14","cited_by_count":1,"area":"deeprl"},{"id":"2310.16655","title":"Towards Control-Centric Representations in Reinforcement Learning from Images","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2408.13498","title":"Rethinking State Disentanglement in Causal Reinforcement Learning","created":"2024-08-24","cited_by_count":0,"area":"deeprl"},{"id":"2411.04056","title":"Problem Space Transformations for Out-of-Distribution Generalisation in Behavioural Cloning","created":"2024-11-06","cited_by_count":0,"area":"offlinerl"},{"id":"2504.04164","title":"MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learning","created":"2025-04-05","cited_by_count":0,"area":"deeprl"},{"id":"2512.05172","title":"Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning","created":"2025-12-04","cited_by_count":0,"area":"mllm"},{"id":"2603.07437","title":"Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2606.16489","title":"BRICKS-WM: Building Reusability via Interface Composition Kinetics for Structured World Models","created":"2026-06-15","cited_by_count":0,"area":"wm"},{"id":"2607.06640","title":"What a World Model Represents Is Three Questions","created":"2026-07-07","cited_by_count":0,"area":"wm"},{"id":"2609.21474","title":"MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation","created":"2026-09-18","cited_by_count":0,"area":"diffusion"},{"id":"2609.30667","title":"StarWM: Self-Supervised Trained Attention Routing for Robust World Models","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"id":"2610.00727","title":"CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorization","created":"2026-09-30","cited_by_count":0,"area":"wm"}],"next_cursor":null}