{"total":68,"rows":[{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379,"area":"offlinerl"},{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2412.13877","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","created":"2024-12-18","cited_by_count":175,"area":"offlinerl"},{"id":"2403.03949","title":"Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation","created":"2024-03-06","cited_by_count":144,"area":"offlinerl"},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138,"area":"offlinerl"},{"id":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48,"area":"offlinerl"},{"id":"2309.11359","title":"Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning","created":"2023-09-20","cited_by_count":31,"area":"offlinerl"},{"id":"2306.00323","title":"Thought Cloning: Learning to Think while Acting by Imitating Human Thinking","created":"2023-06-01","cited_by_count":30,"area":"offlinerl"},{"id":"2311.12996","title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","created":"2023-11-21","cited_by_count":30,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2409.01369","title":"Imitating Language via Scalable Inverse Reinforcement Learning","created":"2024-09-02","cited_by_count":21,"area":"offlinerl"},{"id":"2506.05294","title":"A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search","created":"2025-06-05","cited_by_count":17,"area":"offlinerl"},{"id":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","cited_by_count":14,"area":"offlinerl"},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2401.16398","title":"Zero-shot Imitation Policy via Search in Demonstration Dataset","created":"2024-01-29","cited_by_count":13,"area":"offlinerl"},{"id":"2306.09712","title":"Semi-Offline Reinforcement Learning for Optimized Text Generation","created":"2023-06-16","cited_by_count":12,"area":"offlinerl"},{"id":"2402.03081","title":"Preference-Conditioned Language-Guided Abstraction","created":"2024-02-05","cited_by_count":12,"area":"offlinerl"},{"id":"2506.07505","title":"Reinforcement Learning via Implicit Imitation Guidance","created":"2025-06-09","cited_by_count":12,"area":"offlinerl"},{"id":"2306.13412","title":"CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning","created":"2023-06-23","cited_by_count":11,"area":"offlinerl"},{"id":"2311.08384","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","created":"2023-11-14","cited_by_count":11,"area":"offlinerl"},{"id":"2408.10504","title":"QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning","created":"2024-08-20","cited_by_count":10,"area":"offlinerl"},{"id":"2411.05193","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","created":"2024-11-07","cited_by_count":10,"area":"offlinerl"},{"id":"2502.06051","title":"Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits","created":"2025-02-09","cited_by_count":10,"area":"offlinerl"},{"id":"2502.13519","title":"MILE: Model-based Intervention Learning","created":"2025-02-19","cited_by_count":10,"area":"offlinerl"},{"id":"2410.14069","title":"Rethinking Optimal Transport in Offline Reinforcement Learning","created":"2024-10-17","cited_by_count":9,"area":"offlinerl"},{"id":"2410.24108","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","created":"2024-10-31","cited_by_count":8,"area":"offlinerl"},{"id":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2312.03446","title":"Visual Hindsight Self-Imitation Learning for Interactive Navigation","created":"2023-12-05","cited_by_count":6,"area":"offlinerl"},{"id":"2512.02486","title":"Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts","created":"2025-12-02","cited_by_count":6,"area":"offlinerl"},{"id":"2306.09805","title":"Mimicking Better by Matching the Approximate Action Distribution","created":"2023-06-16","cited_by_count":5,"area":"offlinerl"},{"id":"2604.14265","title":"Reinforcement Learning via Value Gradient Flow","created":"2026-04-15","cited_by_count":5,"area":"offlinerl"},{"id":"2605.00264","title":"Pessimism-Free Offline Learning in General-Sum Games via KL Regularization","created":"2026-04-30","cited_by_count":5,"area":"offlinerl"},{"id":"2312.00054","title":"Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective","created":"2023-11-29","cited_by_count":4,"area":"offlinerl"},{"id":"2402.04154","title":"Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction","created":"2024-02-06","cited_by_count":4,"area":"offlinerl"},{"id":"2405.18757","title":"Multi-objective Cross-task Learning via Goal-conditioned GPT-based Decision Transformers for Surgical Robot Task Automation","created":"2024-05-29","cited_by_count":4,"area":"offlinerl"},{"id":"2505.16242","title":"Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies","created":"2025-05-22","cited_by_count":4,"area":"offlinerl"},{"id":"2306.09082","title":"Behavioral Cloning via Search in Embedded Demonstration Dataset","created":"2023-06-15","cited_by_count":3,"area":"offlinerl"},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"id":"2411.10268","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","created":"2024-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2501.14199","title":"Coordinating Ride-Pooling with Public Transit using Reward-Guided Conservative Q-Learning: An Offline Training and Online Fine-Tuning Reinforcement Learning Framework","created":"2025-01-24","cited_by_count":3,"area":"offlinerl"},{"id":"2502.03698","title":"How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies","created":"2025-02-06","cited_by_count":3,"area":"offlinerl"},{"id":"2606.30445","title":"When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon","created":"2026-06-29","cited_by_count":3,"area":"offlinerl"},{"id":"2404.07185","title":"Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery","created":"2024-04-10","cited_by_count":2,"area":"offlinerl"},{"id":"2412.07057","title":"Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning","created":"2024-12-09","cited_by_count":2,"area":"offlinerl"},{"id":"2505.20335","title":"Language Model Distillation: A Temporal Difference Imitation Learning Perspective","created":"2025-05-24","cited_by_count":2,"area":"offlinerl"},{"id":"2305.03987","title":"Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization","created":"2023-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2311.01589","title":"A Statistical Guarantee for Representation Transfer in Multitask Imitation Learning","created":"2023-11-02","cited_by_count":1,"area":"offlinerl"},{"id":"2404.09717","title":"Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model","created":"2024-04-15","cited_by_count":1,"area":"offlinerl"},{"id":"2410.05715","title":"Demonstration Based Explainable AI for Learning from Demonstration Methods","created":"2024-10-08","cited_by_count":1,"area":"offlinerl"},{"id":"2412.06207","title":"Skill-Enhanced Reinforcement Learning Acceleration from Heterogeneous Demonstrations","created":"2024-12-09","cited_by_count":1,"area":"offlinerl"},{"id":"2503.17865","title":"Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality","created":"2025-03-22","cited_by_count":1,"area":"offlinerl"},{"id":"2510.12638","title":"Expert or not? assessing data quality in offline reinforcement learning","created":"2025-10-14","cited_by_count":1,"area":"offlinerl"},{"id":"2601.00167","title":"Online Finetuning Decision Transformers with Pure RL Gradients","created":"2026-01-01","cited_by_count":1,"area":"offlinerl"},{"id":"2405.20351","title":"Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression","created":"2024-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2411.07514","title":"Robust Offline Reinforcement Learning for Non-Markovian Decision Processes","created":"2024-11-12","cited_by_count":0,"area":"offlinerl"},{"id":"2503.02311","title":"Target Return Optimizer for Multi-Game Decision Transformer","created":"2025-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2602.20643","title":"TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer","created":"2026-02-24","cited_by_count":0,"area":"offlinerl"},{"id":"2603.22713","title":"Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Value Flow Mechanism","created":"2026-03-24","cited_by_count":0,"area":"offlinerl"},{"id":"2604.13175","title":"Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarization","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2604.13966","title":"Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation","created":"2026-04-15","cited_by_count":0,"area":"offlinerl"},{"id":"2604.26516","title":"Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning","created":"2026-04-29","cited_by_count":0,"area":"offlinerl"},{"id":"2605.12000","title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","created":"2026-05-12","cited_by_count":0,"area":"offlinerl"},{"id":"2605.30903","title":"Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach","created":"2026-05-29","cited_by_count":0,"area":"offlinerl"},{"id":"2606.18537","title":"Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents","created":"2026-06-16","cited_by_count":0,"area":"offlinerl"},{"id":"2606.20206","title":"Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random","created":"2026-06-18","cited_by_count":0,"area":"offlinerl"},{"id":"2609.33291","title":"The Statistical Benefits of Multiple Responses for Learning from Demonstrations","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"}],"next_cursor":null}