{"total":79,"rows":[{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115,"area":"offlinerl"},{"id":"1807.09936","title":"Multi-Agent Generative Adversarial Imitation Learning","created":"2018-07-26","cited_by_count":100,"area":"offlinerl"},{"id":"2106.00672","title":"What Matters for Adversarial Imitation Learning?","created":"2021-06-01","cited_by_count":70,"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":"1906.08113","title":"Wasserstein Adversarial Imitation Learning","created":"2019-06-19","cited_by_count":60,"area":"offlinerl"},{"id":"2005.14310","title":"Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning","created":"2020-05-28","cited_by_count":53,"area":"offlinerl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"id":"1805.11240","title":"Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning","created":"2018-05-29","cited_by_count":39,"area":"offlinerl"},{"id":"2006.15061","title":"Intrinsic Reward Driven Imitation Learning via Generative Model","created":"2020-06-26","cited_by_count":35,"area":"offlinerl"},{"id":"2008.09167","title":"Imitation Learning with Sinkhorn Distances","created":"2020-08-20","cited_by_count":30,"area":"offlinerl"},{"id":"2206.09314","title":"Robust Imitation Learning against Variations in Environment Dynamics","created":"2022-06-19","cited_by_count":26,"area":"offlinerl"},{"id":"2311.03351","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","created":"2023-11-06","cited_by_count":26,"area":"offlinerl"},{"id":"2309.05915","title":"ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning","created":"2023-09-12","cited_by_count":25,"area":"offlinerl"},{"id":"1906.09510","title":"Learning Belief Representations for Imitation Learning in POMDPs","created":"2019-06-22","cited_by_count":24,"area":"offlinerl"},{"id":"2509.20478","title":"Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations","created":"2025-09-24","cited_by_count":24,"area":"offlinerl"},{"id":"2010.01207","title":"$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning","created":"2020-10-02","cited_by_count":20,"area":"offlinerl"},{"id":"2305.17198","title":"A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem","created":"2023-05-26","cited_by_count":19,"area":"offlinerl"},{"id":"1803.05402","title":"Imitation Learning with Concurrent Actions in 3D Games","created":"2018-03-14","cited_by_count":18,"area":"offlinerl"},{"id":"2407.00699","title":"Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning","created":"2024-06-30","cited_by_count":17,"area":"offlinerl"},{"id":"2404.19456","title":"A Survey of Imitation Learning Methods, Environments and Metrics","created":"2024-04-30","cited_by_count":16,"area":"offlinerl"},{"id":"2512.03028","title":"SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control","created":"2025-12-02","cited_by_count":15,"area":"offlinerl"},{"id":"2105.10066","title":"A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control","created":"2021-05-21","cited_by_count":13,"area":"offlinerl"},{"id":"1909.06769","title":"VILD: Variational Imitation Learning with Diverse-quality Demonstrations","created":"2019-09-15","cited_by_count":12,"area":"offlinerl"},{"id":"2106.06499","title":"Policy Gradient Bayesian Robust Optimization for Imitation Learning","created":"2021-06-11","cited_by_count":11,"area":"offlinerl"},{"id":"2204.11446","title":"Imitation Learning from Observations under Transition Model Disparity","created":"2022-04-25","cited_by_count":11,"area":"offlinerl"},{"id":"2306.10259","title":"Active Policy Improvement from Multiple Black-box Oracles","created":"2023-06-17","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":"2206.10598","title":"A deep inverse reinforcement learning approach to route choice modeling with context-dependent rewards","created":"2022-06-18","cited_by_count":10,"area":"offlinerl"},{"id":"2412.18855","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","created":"2024-12-25","cited_by_count":9,"area":"offlinerl"},{"id":"2109.05940","title":"Cross Domain Robot Imitation with Invariant Representation","created":"2021-09-13","cited_by_count":8,"area":"offlinerl"},{"id":"1909.11468","title":"Independent Generative Adversarial Self-Imitation Learning in Cooperative Multiagent Systems","created":"2019-09-25","cited_by_count":7,"area":"offlinerl"},{"id":"2505.03209","title":"DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning","created":"2025-05-06","cited_by_count":7,"area":"offlinerl"},{"id":"2002.10525","title":"Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic","created":"2020-02-24","cited_by_count":6,"area":"offlinerl"},{"id":"2205.03484","title":"Diverse Imitation Learning via Self-Organizing Generative Models","created":"2022-05-06","cited_by_count":5,"area":"offlinerl"},{"id":"2301.11426","title":"Model-based Offline Reinforcement Learning with Local Misspecification","created":"2023-01-26","cited_by_count":5,"area":"offlinerl"},{"id":"2404.02407","title":"Decision Transformer as a Foundation Model for Partially Observable Continuous Control","created":"2024-04-03","cited_by_count":5,"area":"offlinerl"},{"id":"2405.14114","title":"Offline Reinforcement Learning from Datasets with Structured Non-Stationarity","created":"2024-05-23","cited_by_count":5,"area":"offlinerl"},{"id":"2503.14259","title":"Quantization-Free Autoregressive Action Transformer","created":"2025-03-18","cited_by_count":5,"area":"offlinerl"},{"id":"2001.07798","title":"Augmenting GAIL with BC for sample efficient imitation learning","created":"2020-01-21","cited_by_count":4,"area":"offlinerl"},{"id":"2203.10905","title":"Self-Imitation Learning from Demonstrations","created":"2022-03-21","cited_by_count":4,"area":"offlinerl"},{"id":"2303.03811","title":"Environment Transformer and Policy Optimization for Model-Based Offline Reinforcement Learning","created":"2023-03-07","cited_by_count":4,"area":"offlinerl"},{"id":"2408.11632","title":"Optimizing Interpretable Decision Tree Policies for Reinforcement Learning","created":"2024-08-21","cited_by_count":4,"area":"offlinerl"},{"id":"2112.06054","title":"Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency","created":"2021-12-11","cited_by_count":3,"area":"offlinerl"},{"id":"2206.02095","title":"ARC - Actor Residual Critic for Adversarial Imitation Learning","created":"2022-06-05","cited_by_count":3,"area":"offlinerl"},{"id":"2407.04856","title":"Explorative Imitation Learning: A Path Signature Approach for Continuous Environments","created":"2024-07-05","cited_by_count":3,"area":"offlinerl"},{"id":"2501.14856","title":"Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation","created":"2025-01-24","cited_by_count":3,"area":"offlinerl"},{"id":"2512.10510","title":"Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning","created":"2025-12-11","cited_by_count":3,"area":"offlinerl"},{"id":"2008.11804","title":"Deep Inverse Reinforcement Learning for Structural Evolution of Small Molecules","created":"2020-07-24","cited_by_count":2,"area":"offlinerl"},{"id":"2311.02502","title":"MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters","created":"2023-11-04","cited_by_count":2,"area":"offlinerl"},{"id":"2507.21533","title":"Model Predictive Adversarial Imitation Learning for Planning from Observation","created":"2025-07-29","cited_by_count":2,"area":"offlinerl"},{"id":"2605.15603","title":"Offline Reinforcement Learning with Universal Horizon Models","created":"2026-05-15","cited_by_count":2,"area":"offlinerl"},{"id":"1810.01108","title":"Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning","created":"2018-10-02","cited_by_count":1,"area":"offlinerl"},{"id":"2007.02520","title":"Explaining Fast Improvement in Online Imitation Learning","created":"2020-07-06","cited_by_count":1,"area":"offlinerl"},{"id":"2105.03019","title":"Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectories","created":"2021-05-07","cited_by_count":1,"area":"offlinerl"},{"id":"2206.11004","title":"Auto-Encoding Adversarial Imitation Learning","created":"2022-06-22","cited_by_count":1,"area":"offlinerl"},{"id":"2403.17456","title":"Imitating Cost-Constrained Behaviors in Reinforcement Learning","created":"2024-03-26","cited_by_count":1,"area":"offlinerl"},{"id":"2501.01669","title":"Inversely Learning Transferable Rewards via Abstracted States","created":"2025-01-03","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":"1907.11842","title":"Self-Imitation Learning of Locomotion Movements through Termination Curriculum","created":"2019-07-27","cited_by_count":0,"area":"offlinerl"},{"id":"2002.01059","title":"Preventing Imitation Learning with Adversarial Policy Ensembles","created":"2020-01-31","cited_by_count":0,"area":"offlinerl"},{"id":"2111.02354","title":"Smooth Imitation Learning via Smooth Costs and Smooth Policies","created":"2021-11-03","cited_by_count":0,"area":"offlinerl"},{"id":"2111.08156","title":"Improving Learning from Demonstrations by Learning from Experience","created":"2021-11-16","cited_by_count":0,"area":"offlinerl"},{"id":"2112.08094","title":"Automatic tuning of hyper-parameters of reinforcement learning algorithms using Bayesian optimization with behavioral cloning","created":"2021-12-15","cited_by_count":0,"area":"offlinerl"},{"id":"2204.04157","title":"Custom Sine Waves Are Enough for Imitation Learning of Bipedal Gaits with Different Styles","created":"2022-04-08","cited_by_count":0,"area":"offlinerl"},{"id":"2304.10914","title":"Self-Supervised Adversarial Imitation Learning","created":"2023-04-21","cited_by_count":0,"area":"offlinerl"},{"id":"2408.10113","title":"Enhancing Reinforcement Learning Through Guided Search","created":"2024-08-19","cited_by_count":0,"area":"offlinerl"},{"id":"2502.11937","title":"FitLight: Federated Imitation Learning for Plug-and-Play Autonomous Traffic Signal Control","created":"2025-02-17","cited_by_count":0,"area":"offlinerl"},{"id":"2509.24784","title":"Quantifying Generalisation in Imitation Learning","created":"2025-09-29","cited_by_count":0,"area":"offlinerl"},{"id":"2512.08052","title":"An Introduction to Deep Reinforcement and Imitation Learning","created":"2025-12-08","cited_by_count":0,"area":"offlinerl"},{"id":"2602.03305","title":"medR: Reward Engineering for Clinical Offline Reinforcement Learning via Tri-Drive Potential Functions","created":"2026-02-03","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":"2603.24883","title":"Learning to Staff: Offline Reinforcement Learning and Fine-Tuned LLMs for Warehouse Staffing Optimization","created":"2026-03-25","cited_by_count":0,"area":"offlinerl"},{"id":"2604.02438","title":"Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models","created":"2026-04-02","cited_by_count":0,"area":"offlinerl"},{"id":"2604.03523","title":"Optimizing Neurorobot Policy under Limited Demonstration Data through Preference Regret","created":"2026-04-04","cited_by_count":0,"area":"offlinerl"},{"id":"2607.02034","title":"ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments","created":"2026-07-02","cited_by_count":0,"area":"offlinerl"},{"id":"2609.15631","title":"Flow-Matched Motion Priors: Online Optimal-Transport Rewards for Imitation Learning","created":"2026-09-14","cited_by_count":0,"area":"offlinerl"},{"id":"2609.38407","title":"Disagreement-Regularized Imitation Learning for Image-Based Continuous Control with Gaussian and Beta Policies","created":"2026-09-29","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}