{"total":121,"rows":[{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238,"area":"offlinerl"},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2406.17098","title":"Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making","created":"2024-06-24","cited_by_count":56,"area":"deeprl"},{"id":"2503.14858","title":"1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities","created":"2025-03-19","cited_by_count":45,"area":"deeprl"},{"id":"2503.05153","title":"Generative Trajectory Stitching through Diffusion Composition","created":"2025-03-07","cited_by_count":41,"area":"diffusion"},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2603.12231","title":"Temporal Straightening for Latent Planning","created":"2026-03-12","cited_by_count":38,"area":"wm"},{"id":"2310.20141","title":"Contrastive Difference Predictive Coding","created":"2023-10-31","cited_by_count":36,"area":null},{"id":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31,"area":"deeprl"},{"id":"2509.20478","title":"Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations","created":"2025-09-24","cited_by_count":24,"area":"offlinerl"},{"id":"2505.12737","title":"Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning","created":"2025-05-19","cited_by_count":23,"area":"offlinerl"},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2601.00844","title":"Value-guided action planning with JEPA world models","created":"2025-12-28","cited_by_count":21,"area":"wm"},{"id":"2605.07278","title":"Predictive but Not Plannable: RC-aux for Latent World Models","created":"2026-05-08","cited_by_count":19,"area":"wm"},{"id":"2403.04082","title":"Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference","created":"2024-03-06","cited_by_count":17,"area":null},{"id":"2407.08464","title":"TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations","created":"2024-07-11","cited_by_count":17,"area":"deeprl"},{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"area":"deeprl"},{"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":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"id":"2510.06714","title":"Dual Goal Representations","created":"2025-10-08","cited_by_count":16,"area":"deeprl"},{"id":"2509.06782","title":"Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning","created":"2025-09-08","cited_by_count":15,"area":"offlinerl"},{"id":"2603.04553","title":"Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling","created":"2026-03-04","cited_by_count":15,"area":"wm"},{"id":"2502.05454","title":"Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following","created":"2025-02-08","cited_by_count":14,"area":null},{"id":"2505.23527","title":"Normalizing Flows are Capable Models for Continuous Control","created":"2025-05-29","cited_by_count":14,"area":"deeprl"},{"id":"2506.21427","title":"Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning","created":"2025-06-26","cited_by_count":14,"area":"diffusion"},{"id":"2506.00895","title":"State-Covering Trajectory Stitching for Diffusion Planners","created":"2025-06-01","cited_by_count":13,"area":"diffusion"},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2506.07744","title":"Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning","created":"2025-06-09","cited_by_count":12,"area":"offlinerl"},{"id":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","cited_by_count":12,"area":"offlinerl"},{"id":"2510.22512","title":"Transitive RL: Value Learning via Divide and Conquer","created":"2025-10-26","cited_by_count":12,"area":"deeprl"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2505.14975","title":"Flattening Hierarchies with Policy Bootstrapping","created":"2025-05-20","cited_by_count":11,"area":"synth"},{"id":"2602.05533","title":"Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach","created":"2026-02-05","cited_by_count":11,"area":"diffusion"},{"id":"2402.13037","title":"Align Your Intents: Offline Imitation Learning via Optimal Transport","created":"2024-02-20","cited_by_count":8,"area":"offlinerl"},{"id":"2406.00324","title":"Do's and Don'ts: Learning Desirable Skills with Instruction Videos","created":"2024-06-01","cited_by_count":8,"area":null},{"id":"2507.18809","title":"Test-time Offline Reinforcement Learning on Goal-related Experience","created":"2025-07-24","cited_by_count":8,"area":"offlinerl"},{"id":"2510.07257","title":"Test-Time Graph Search for Goal-Conditioned Reinforcement Learning","created":"2025-10-08","cited_by_count":8,"area":"deeprl"},{"id":"2511.07730","title":"Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning","created":"2025-11-11","cited_by_count":8,"area":"deeprl"},{"id":"2607.25337","title":"Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control","created":"2026-07-28","cited_by_count":8,"area":"wm"},{"id":"2602.02722","title":"Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion","created":"2026-02-02","cited_by_count":7,"area":"deeprl"},{"id":"2608.09853","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","created":"2026-08-10","cited_by_count":7,"area":"alignment"},{"id":"2306.04026","title":"Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theory","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2501.13457","title":"Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks","created":"2025-01-23","cited_by_count":6,"area":null},{"id":"2505.05691","title":"Physics-informed Temporal Difference Metric Learning for Robot Motion Planning","created":"2025-05-09","cited_by_count":6,"area":null},{"id":"2505.13144","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":6,"area":"offlinerl"},{"id":"2510.08218","title":"Expressive Value Learning for Scalable Offline Reinforcement Learning","created":"2025-10-09","cited_by_count":6,"area":"diffusion"},{"id":"2512.12046","title":"Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning","created":"2025-12-12","cited_by_count":6,"area":"deeprl"},{"id":"2506.18847","title":"Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric Planning","created":"2025-06-23","cited_by_count":5,"area":"offlinerl"},{"id":"2602.03389","title":"Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL","created":"2026-02-03","cited_by_count":5,"area":"offlinerl"},{"id":"2602.05031","title":"Laplacian Representations for Decision-Time Planning","created":"2026-02-04","cited_by_count":5,"area":"deeprl"},{"id":"2311.03534","title":"PcLast: Discovering Plannable Continuous Latent States","created":"2023-11-06","cited_by_count":4,"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":"2410.08751","title":"Zero-Shot Offline Imitation Learning via Optimal Transport","created":"2024-10-11","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":"2505.19717","title":"Extremum Flow Matching for Offline Goal Conditioned Reinforcement Learning","created":"2025-05-26","cited_by_count":3,"area":"diffusion"},{"id":"2506.21044","title":"Efficient Skill Discovery via Regret-Aware Optimization","created":"2025-06-26","cited_by_count":3,"area":"deeprl"},{"id":"2509.23802","title":"STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2603.13971","title":"Chunk-Guided Q-Learning","created":"2026-03-14","cited_by_count":3,"area":"offlinerl"},{"id":"2604.17551","title":"SVL: Goal-Conditioned Reinforcement Learning as Survival Learning","created":"2026-04-19","cited_by_count":3,"area":"deeprl"},{"id":"2608.30640","title":"Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL","created":"2026-08-31","cited_by_count":3,"area":"deeprl"},{"id":"2609.34575","title":"Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning","created":"2026-09-28","cited_by_count":3,"area":"offlinerl"},{"id":"2409.08724","title":"Quasimetric Value Functions with Dense Rewards","created":"2024-09-13","cited_by_count":2,"area":"deeprl"},{"id":"2410.05225","title":"ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Control","created":"2024-10-07","cited_by_count":2,"area":"deeprl"},{"id":"2509.25550","title":"Unifying Agent Interaction and World Information for Multi-agent Coordination","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2512.07976","title":"VLD: Visual Language Goal Distance for Reinforcement Learning Navigation","created":"2025-12-08","cited_by_count":2,"area":"deeprl"},{"id":"2603.09400","title":"Reward Prediction with Factorized World States","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2604.08960","title":"Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning","created":"2026-04-10","cited_by_count":2,"area":"offlinerl"},{"id":"2605.03075","title":"Refining Compositional Diffusion for Reliable Long-Horizon Planning","created":"2026-05-04","cited_by_count":2,"area":null},{"id":"2605.06145","title":"Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization","created":"2026-05-07","cited_by_count":2,"area":"deeprl"},{"id":"2605.29782","title":"Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.07855","title":"NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2607.13612","title":"The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models","created":"2026-07-15","cited_by_count":2,"area":"wm"},{"id":"2407.01991","title":"Generation of Geodesics with Actor-Critic Reinforcement Learning to Predict Midpoints","created":"2024-07-02","cited_by_count":1,"area":"deeprl"},{"id":"2506.09276","title":"Learning The Minimum Action Distance","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2510.17059","title":"Consistent Zero-Shot Imitation with Contrastive Goal Inference","created":"2025-10-20","cited_by_count":1,"area":"offlinerl"},{"id":"2511.03187","title":"Periodic Skill Discovery","created":"2025-11-05","cited_by_count":1,"area":"deeprl"},{"id":"2601.22496","title":"Action-Sufficient Goal Representations","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2602.23280","title":"Mollified Value Learning","created":"2026-02-26","cited_by_count":1,"area":"deeprl"},{"id":"2604.20627","title":"Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning","created":"2026-04-22","cited_by_count":1,"area":"wm"},{"id":"2605.06470","title":"Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies","created":"2026-05-07","cited_by_count":1,"area":"offlinerl"},{"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":"2605.25740","title":"Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-25","cited_by_count":1,"area":"offlinerl"},{"id":"2605.28127","title":"Adaptive Coarse-to-Fine Subgoal Refinement for Long-Horizon Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2609.02237","title":"Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL","created":"2026-09-02","cited_by_count":1,"area":"offlinerl"},{"id":"2406.10795","title":"Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2410.16666","title":"QuasiNav: Asymmetric Cost-Aware Navigation Planning with Constrained Quasimetric Reinforcement Learning","created":"2024-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2506.02577","title":"Reachability Weighted Offline Goal-conditioned Resampling","created":"2025-06-03","cited_by_count":0,"area":"offlinerl"},{"id":"2507.13706","title":"GOSPA and T-GOSPA quasi-metrics for evaluation of multi-object tracking algorithms","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2512.17846","title":"Planning as Descent: Goal-Conditioned Latent Trajectory Synthesis in Learned Energy Landscapes","created":"2025-12-19","cited_by_count":0,"area":"deeprl"},{"id":"2602.05459","title":"Beyond Success Rates: Trainability and Extractability for Offline GCRL","created":"2026-02-05","cited_by_count":0,"area":"offlinerl"},{"id":"2602.12087","title":"Geometry of Uncertainty: Learning Metric Spaces for Multimodal State Estimation in RL","created":"2026-02-12","cited_by_count":0,"area":"deeprl"},{"id":"2602.12245","title":"Intrinsic-Energy Joint Embedding Predictive Architectures Induce Quasimetric Spaces","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2605.30503","title":"Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact Dynamics","created":"2026-05-28","cited_by_count":0,"area":"deeprl"},{"id":"2606.04188","title":"Dual Advantage Fields","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2606.06618","title":"ChronoForest: Closed-Loop Multi-Tree Diffusion Planning for Efficient Bridge Search and Route Composition","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":"100"}