{"total":57,"rows":[{"id":"2511.09515","title":"WMPO: World Model-based Policy Optimization for Vision-Language-Action Models","created":"2025-11-12","cited_by_count":70,"area":"wm"},{"id":"2509.19301","title":"Residual Off-Policy RL for Finetuning Behavior Cloning Policies","created":"2025-09-23","cited_by_count":55,"area":null},{"id":"2601.14234","title":"Q-learning with Adjoint Matching","created":"2026-01-20","cited_by_count":37,"area":"diffusion"},{"id":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23,"area":"deeprl"},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"id":"2510.06714","title":"Dual Goal Representations","created":"2025-10-08","cited_by_count":16,"area":"deeprl"},{"id":"2510.07650","title":"Value Flows","created":"2025-10-09","cited_by_count":15,"area":"deeprl"},{"id":"2507.12549","title":"The Serial Scaling Hypothesis","created":"2025-07-16","cited_by_count":13,"area":null},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"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":"2510.07730","title":"DEAS: DEtached value learning with Action Sequence for Scalable Offline RL","created":"2025-10-09","cited_by_count":10,"area":"offlinerl"},{"id":"2511.07730","title":"Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning","created":"2025-11-11","cited_by_count":8,"area":"deeprl"},{"id":"2602.02722","title":"Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion","created":"2026-02-02","cited_by_count":7,"area":"deeprl"},{"id":"2602.19634","title":"Compositional Planning with Jumpy World Models","created":"2026-02-23","cited_by_count":7,"area":"wm"},{"id":"2510.08218","title":"Expressive Value Learning for Scalable Offline Reinforcement Learning","created":"2025-10-09","cited_by_count":6,"area":"diffusion"},{"id":"2605.02572","title":"On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length","created":"2026-05-04","cited_by_count":6,"area":null},{"id":"2606.11087","title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","created":"2026-06-09","cited_by_count":6,"area":"offlinerl"},{"id":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"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":"2606.08015","title":"Q-VGM: Q-Guided Value-Gradient Matching for Offline-to-Online RL of Flow-Matching VLA Policies","created":"2026-06-06","cited_by_count":3,"area":"vla"},{"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":"2605.01663","title":"Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning","created":"2026-05-03","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":"2605.06156","title":"Entropy-Regularized Adjoint Matching for Offline Reinforcement Learning","created":"2026-05-07","cited_by_count":2,"area":"diffusion"},{"id":"2605.15603","title":"Offline Reinforcement Learning with Universal Horizon Models","created":"2026-05-15","cited_by_count":2,"area":"offlinerl"},{"id":"2605.22711","title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-21","cited_by_count":2,"area":"offlinerl"},{"id":"2605.31273","title":"Survival Reinforcement Learning: Toward Scalable Self-Supervised RL","created":"2026-05-29","cited_by_count":2,"area":"deeprl"},{"id":"2606.17551","title":"Reversal Q-Learning","created":"2026-06-16","cited_by_count":2,"area":"diffusion"},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"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":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2604.26326","title":"Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control","created":"2026-04-29","cited_by_count":1,"area":"lr"},{"id":"2605.05544","title":"Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning","created":"2026-05-07","cited_by_count":1,"area":"offlinerl"},{"id":"2607.20834","title":"Offline RL with Hierarchical Action Chunking","created":"2026-07-23","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":"2602.05459","title":"Beyond Success Rates: Trainability and Extractability for Offline GCRL","created":"2026-02-05","cited_by_count":0,"area":"offlinerl"},{"id":"2604.24558","title":"Hierarchical Behaviour Spaces","created":"2026-04-27","cited_by_count":0,"area":"deeprl"},{"id":"2605.01862","title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","created":"2026-05-03","cited_by_count":0,"area":"ssm"},{"id":"2605.11009","title":"ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network","created":"2026-05-10","cited_by_count":0,"area":"offlinerl"},{"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":"2605.16863","title":"Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning","created":"2026-05-16","cited_by_count":0,"area":"diffusion"},{"id":"2605.23138","title":"Classical State Preparation for Variational Quantum Algorithms via Reinforcement Learning","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.23551","title":"Goal-Conditioned Agents that Learn Everything All at Once","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.26282","title":"Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization","created":"2026-05-25","cited_by_count":0,"area":"wm"},{"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":"2606.16515","title":"Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.17011","title":"ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"vla"},{"id":"2606.21136","title":"Horizon Adaptive Offline Policy Learning via Value Stitching","created":"2026-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2608.27678","title":"SegBench-GC: Testing Segmentation Invariance in Multi-Step Offline Goal-Conditioned Reinforcement Learning","created":"2026-08-27","cited_by_count":0,"area":"offlinerl"},{"id":"2609.22085","title":"SeeQ: Training Generalist Value Functions for Long-Horizon Robotic Manipulation","created":"2026-09-18","cited_by_count":0,"area":"vla"},{"id":"2609.33259","title":"GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences","created":"2026-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35880","title":"From Static Policies to Adaptive Priors in Offline Reinforcement Learning","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2610.12135","title":"Q-Shaped Options for Hierarchical Reinforcement Learning","created":"2026-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2610.19129","title":"Imagining Goals with Geometric Horizon Models for Policy Generalization","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}