{"total":121,"rows":[{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197,"area":null},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121,"area":null},{"id":"2206.08686","title":"Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning","created":"2022-06-17","cited_by_count":119,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2306.13229","title":"TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning","created":"2023-06-22","cited_by_count":57,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2310.20141","title":"Contrastive Difference Predictive Coding","created":"2023-10-31","cited_by_count":36,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2205.08129","title":"Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space","created":"2022-05-17","cited_by_count":31,"area":null},{"id":"2305.17625","title":"Cross-Domain Policy Adaptation via Value-Guided Data Filtering","created":"2023-05-28","cited_by_count":31,"area":null},{"id":"2207.04703","title":"Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"2210.06601","title":"Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks","created":"2022-10-12","cited_by_count":25,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2311.01394","title":"Learning Realistic Traffic Agents in Closed-loop","created":"2023-11-02","cited_by_count":24,"area":null},{"id":"2306.03346","title":"Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2212.02779","title":"PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement","created":"2022-12-06","cited_by_count":21,"area":null},{"id":"2211.11802","title":"Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning","created":"2022-11-21","cited_by_count":20,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"area":null},{"id":"2301.08502","title":"Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning","created":"2023-01-20","cited_by_count":17,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2302.01724","title":"Reinforcing User Retention in a Billion Scale Short Video Recommender System","created":"2023-02-03","cited_by_count":15,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2409.15844","title":"Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection","created":"2024-09-24","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2402.04647","title":"Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference","created":"2024-02-07","cited_by_count":14,"area":null},{"id":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2405.18917","title":"Causal Action Influence Aware Counterfactual Data Augmentation","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2312.02682","title":"H-GAP: Humanoid Control with a Generalist Planner","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2401.05442","title":"Functional Graphical Models: Structure Enables Offline Data-Driven Optimization","created":"2024-01-08","cited_by_count":11,"area":null},{"id":"2206.02620","title":"ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor","created":"2022-06-01","cited_by_count":10,"area":null},{"id":"2402.06187","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2306.06253","title":"Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2412.05718","title":"RLZero: Direct Policy Inference from Language Without In-Domain Supervision","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2210.08153","title":"CUP: Critic-Guided Policy Reuse","created":"2022-10-15","cited_by_count":6,"area":null},{"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":"2310.03984","title":"AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2408.10286","title":"GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching","created":"2024-08-19","cited_by_count":5,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2402.12498","title":"Feudal Networks for Visual Navigation","created":"2024-02-19","cited_by_count":4,"area":null},{"id":"2405.14790","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2503.04969","title":"Data-Efficient Learning from Human Interventions for Mobile Robots","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2205.12418","title":"Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2307.13101","title":"Contrastive Example-Based Control","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2312.15965","title":"Efficient Reinforcement Learning via Decoupling Exploration and Utilization","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2401.09243","title":"DiffClone: Enhanced Behaviour Cloning in Robotics with Diffusion-Driven Policy Learning","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2410.23952","title":"Scalable Kernel Inverse Optimization","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2505.00304","title":"Reinforcement Learning with Continuous Actions Under Unmeasured Confounding","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2602.09580","title":"SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2605.07727","title":"Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2209.07074","title":"On the Reuse Bias in Off-Policy Reinforcement Learning","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2209.08351","title":"Sample-Efficient Multi-Agent Reinforcement Learning with Demonstrations for Flocking Control","created":"2022-09-17","cited_by_count":2,"area":null},{"id":"2303.10180","title":"Towards Real-World Applications of Personalized Anesthesia Using Policy Constraint Q Learning for Propofol Infusion Control","created":"2023-03-17","cited_by_count":2,"area":null},{"id":"2303.10828","title":"DataLight: Offline Data-Driven Traffic Signal Control","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2305.11340","title":"Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models","created":"2023-05-18","cited_by_count":2,"area":null},{"id":"2403.01768","title":"Canonical Form of Datatic Description in Control Systems","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2411.04138","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2601.20116","title":"In-Context Reinforcement Learning From Suboptimal Historical Data","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2602.12390","title":"Rational Neural Networks have Expressivity Advantages","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2603.15857","title":"Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2605.05857","title":"Offline Reinforcement Learning for Rotation Profile Control in Tokamaks","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2609.01596","title":"Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2112.10877","title":"AGPNet -- Autonomous Grading Policy Network","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2201.12163","title":"Biases in In Silico Evaluation of Molecular Optimization Methods and Bias-Reduced Evaluation Methodology","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2204.11897","title":"Reinforcement Teaching","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2307.06758","title":"Layered controller synthesis for dynamic multi-agent systems","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2408.07753","title":"How to Solve Contextual Goal-Oriented Problems with Offline Datasets?","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2411.07372","title":"Identifying Differential Patient Care Through Inverse Intent Inference","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2502.06584","title":"Alert: Learning Trigger Functions for Early Classification of Time Series using Deep-RL","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2504.18235","title":"BiasBench: A reproducible benchmark for tuning the biases of event cameras","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2605.09009","title":"Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.20036","title":"D$^3$-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.27877","title":"SPAR: Support-Preserving Action Rectification","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.19656","title":"DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.07542","title":"An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadruped Navigation Research Loop","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2209.08347","title":"Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control","created":"2022-09-17","cited_by_count":0,"area":null},{"id":"2211.17249","title":"Efficient Reinforcement Learning Through Trajectory Generation","created":"2022-11-30","cited_by_count":0,"area":null},{"id":"2302.13087","title":"Gauss-Newton Temporal Difference Learning with Nonlinear Function Approximation","created":"2023-02-25","cited_by_count":0,"area":null},{"id":"2304.00573","title":"Risk-Sensitive and Robust Model-Based Reinforcement Learning and Planning","created":"2023-04-02","cited_by_count":0,"area":null},{"id":"2312.01544","title":"KEEC: Koopman Embedded Equivariant Control","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2405.12001","title":"Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2411.02933","title":"P-MOSS: Scheduling Main-Memory Indexes Over NUMA Servers Using Next Token Prediction","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2412.00293","title":"Adaptformer: Sequence models as adaptive iterative planners","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2412.19064","title":"Hierarchical Multi-agent Meta-Reinforcement Learning for Cross-channel Bidding","created":"2024-12-26","cited_by_count":0,"area":null}],"next_cursor":"100"}