{"total":85,"rows":[{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452,"area":"offlinerl"},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327,"area":"offlinerl"},{"id":"2410.24185","title":"DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning","created":"2024-10-31","cited_by_count":116,"area":"offlinerl"},{"id":"2305.18459","title":"Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning","created":"2023-05-29","cited_by_count":115,"area":"diffusion"},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89,"area":"offlinerl"},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"area":null},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2410.18907","title":"SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment","created":"2024-10-24","cited_by_count":52,"area":"offlinerl"},{"id":"2105.14859","title":"Consistency Regularization for Variational Auto-Encoders","created":"2021-05-31","cited_by_count":51,"area":null},{"id":"2205.11790","title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","created":"2022-05-24","cited_by_count":50,"area":"offlinerl"},{"id":"2206.08569","title":"Bootstrapped Transformer for Offline Reinforcement Learning","created":"2022-06-17","cited_by_count":37,"area":"offlinerl"},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28,"area":null},{"id":"2111.01365","title":"Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics","created":"2021-11-02","cited_by_count":27,"area":"offlinerl"},{"id":"2209.07364","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","created":"2022-09-15","cited_by_count":27,"area":null},{"id":"2206.05266","title":"Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?","created":"2022-06-10","cited_by_count":24,"area":null},{"id":"2405.16907","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":22,"area":"offlinerl"},{"id":"2203.09365","title":"Semi-Markov Offline Reinforcement Learning for Healthcare","created":"2022-03-17","cited_by_count":18,"area":"offlinerl"},{"id":"2306.04220","title":"Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL","created":"2023-06-07","cited_by_count":18,"area":"offlinerl"},{"id":"2309.05472","title":"LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech","created":"2023-09-11","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":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2206.07166","title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning","created":"2022-06-14","cited_by_count":14,"area":"offlinerl"},{"id":"2208.07811","title":"Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learning","created":"2022-08-15","cited_by_count":13,"area":"offlinerl"},{"id":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","cited_by_count":13,"area":"offlinerl"},{"id":"2411.16959","title":"RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations","created":"2024-11-25","cited_by_count":13,"area":"offlinerl"},{"id":"2506.00895","title":"State-Covering Trajectory Stitching for Diffusion Planners","created":"2025-06-01","cited_by_count":13,"area":"diffusion"},{"id":"2203.08949","title":"Latent-Variable Advantage-Weighted Policy Optimization for Offline RL","created":"2022-03-16","cited_by_count":12,"area":"offlinerl"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","cited_by_count":12,"area":"offlinerl"},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2302.09167","title":"Mixed Traffic Control and Coordination from Pixels","created":"2023-02-17","cited_by_count":10,"area":null},{"id":"2310.18247","title":"Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning","created":"2023-10-27","cited_by_count":10,"area":"offlinerl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2409.08687","title":"xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing","created":"2024-09-13","cited_by_count":9,"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":"2406.12550","title":"Offline Imitation Learning with Model-based Reverse Augmentation","created":"2024-06-18","cited_by_count":8,"area":"offlinerl"},{"id":"2310.17786","title":"Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2306.15156","title":"Learning non-Markovian Decision-Making from State-only Sequences","created":"2023-06-27","cited_by_count":6,"area":"offlinerl"},{"id":"2406.06793","title":"PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer","created":"2024-06-10","cited_by_count":6,"area":"offlinerl"},{"id":"2408.01402","title":"Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer","created":"2024-08-02","cited_by_count":6,"area":"offlinerl"},{"id":"2412.11484","title":"Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents","created":"2024-12-16","cited_by_count":6,"area":"mllm"},{"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":"2301.13019","title":"Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies","created":"2023-01-30","cited_by_count":5,"area":"offlinerl"},{"id":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2309.12815","title":"Improving Generalization in Game Agents with Data Augmentation in Imitation Learning","created":"2023-09-22","cited_by_count":4,"area":"offlinerl"},{"id":"2405.04307","title":"Improving Offline Reinforcement Learning with Inaccurate Simulators","created":"2024-05-07","cited_by_count":4,"area":"offlinerl"},{"id":"2205.09117","title":"Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks","created":"2022-05-18","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":"2309.07578","title":"Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning","created":"2023-09-14","cited_by_count":3,"area":"offlinerl"},{"id":"2408.15593","title":"Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning","created":"2024-08-28","cited_by_count":3,"area":"offlinerl"},{"id":"2111.04345","title":"Off-policy Imitation Learning from Visual Inputs","created":"2021-11-08","cited_by_count":2,"area":"offlinerl"},{"id":"2210.10469","title":"Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation","created":"2022-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2505.07257","title":"DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward","created":"2025-05-12","cited_by_count":2,"area":"wm"},{"id":"2305.12679","title":"Offline Reinforcement Learning with Additional Covering Distributions","created":"2023-05-22","cited_by_count":1,"area":"offlinerl"},{"id":"2306.06329","title":"HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach","created":"2023-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2405.14374","title":"State-Constrained Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":1,"area":"offlinerl"},{"id":"2406.07041","title":"Integrating Domain Knowledge for handling Limited Data in Offline RL","created":"2024-06-11","cited_by_count":1,"area":"offlinerl"},{"id":"2407.03311","title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","created":"2024-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2408.13092","title":"Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning","created":"2024-08-23","cited_by_count":1,"area":"diffusion"},{"id":"2501.17667","title":"CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization","created":"2025-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2504.08704","title":"Offline Reinforcement Learning using Human-Aligned Reward Labeling for Autonomous Emergency Braking in Occluded Pedestrian Crossing","created":"2025-04-11","cited_by_count":1,"area":"offlinerl"},{"id":"2507.02356","title":"Offline Reinforcement Learning with Penalized Action Noise Injection","created":"2025-07-03","cited_by_count":1,"area":"diffusion"},{"id":"2603.02650","title":"Improving Diffusion Planners by Self-Supervised Action Gating with Energies","created":"2026-03-03","cited_by_count":1,"area":"offlinerl"},{"id":"2605.27877","title":"SPAR: Support-Preserving Action Rectification","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2305.02882","title":"Simple Noisy Environment Augmentation for Reinforcement Learning","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2312.02352","title":"Working Backwards: Learning to Place by Picking","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":"2406.04323","title":"ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories","created":"2024-06-06","cited_by_count":0,"area":"deeprl"},{"id":"2408.13452","title":"Data Augmentation for Continual RL via Adversarial Gradient Episodic Memory","created":"2024-08-24","cited_by_count":0,"area":"deeprl"},{"id":"2502.00850","title":"Dual Alignment Maximin Optimization for Offline Model-based RL","created":"2025-02-02","cited_by_count":0,"area":"offlinerl"},{"id":"2505.13925","title":"Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning","created":"2025-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2508.12356","title":"Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data","created":"2025-08-17","cited_by_count":0,"area":"offlinerl"},{"id":"2509.00347","title":"LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning","created":"2025-08-30","cited_by_count":0,"area":"offlinerl"},{"id":"2510.00358","title":"DiSA-IQL: Offline Reinforcement Learning for Robust Soft Robot Control under Distribution Shifts","created":"2025-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2511.03473","title":"Reinforcement Learning Using known Invariances","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2605.13401","title":"Trajectory-Level Data Augmentation for Offline Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"offlinerl"},{"id":"2606.09559","title":"Safe-RULE: Safe Reinforcement UnLEarning","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2606.24078","title":"MinInter: Minimizing Trajectory Interpolation During Data Augmentation for Imitation Learning","created":"2026-06-23","cited_by_count":0,"area":"offlinerl"},{"id":"2607.02288","title":"Generalization in offline RL: The structure is more important than the amount of pessimism","created":"2026-07-02","cited_by_count":0,"area":"offlinerl"},{"id":"2609.20300","title":"Improving Generalization and Robustness in Offline Reinforcement Learning via Boundary-Aware Data Augmentation","created":"2026-08-22","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}