{"total":114,"rows":[{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148,"area":"offlinerl"},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54,"area":null},{"id":"2204.02320","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","created":"2022-04-05","cited_by_count":51,"area":"offlinerl"},{"id":"2110.14754","title":"Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality","created":"2021-10-27","cited_by_count":44,"area":"offlinerl"},{"id":"2109.12750","title":"Learning Multimodal Rewards from Rankings","created":"2021-09-27","cited_by_count":41,"area":"alignment"},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"area":"lr"},{"id":"2509.02722","title":"Planning with Reasoning using Vision Language World Model","created":"2025-09-02","cited_by_count":36,"area":"wm"},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2103.05910","title":"Learning from Imperfect Demonstrations from Agents with Varying Dynamics","created":"2021-03-10","cited_by_count":27,"area":"offlinerl"},{"id":"2010.10181","title":"Robust Imitation Learning from Noisy Demonstrations","created":"2020-10-20","cited_by_count":26,"area":"offlinerl"},{"id":"2103.04909","title":"Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing","created":"2021-03-08","cited_by_count":26,"area":"wm"},{"id":"2206.09314","title":"Robust Imitation Learning against Variations in Environment Dynamics","created":"2022-06-19","cited_by_count":26,"area":"offlinerl"},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2303.02569","title":"Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching","created":"2023-03-05","cited_by_count":24,"area":"offlinerl"},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2106.08314","title":"Causal Navigation by Continuous-time Neural Networks","created":"2021-06-15","cited_by_count":23,"area":"offlinerl"},{"id":"2601.07060","title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","created":"2026-01-11","cited_by_count":21,"area":"vla"},{"id":"2204.10320","title":"SelfD: Self-Learning Large-Scale Driving Policies From the Web","created":"2022-04-21","cited_by_count":18,"area":"driving"},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"area":null},{"id":"2303.00638","title":"MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts","created":"2023-03-01","cited_by_count":18,"area":"offlinerl"},{"id":"2304.00776","title":"Chain-of-Thought Predictive Control","created":"2023-04-03","cited_by_count":18,"area":"lr"},{"id":"2503.03707","title":"Curating Demonstrations using Online Experience","created":"2025-03-05","cited_by_count":18,"area":null},{"id":"2506.11948","title":"SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies","created":"2025-06-13","cited_by_count":18,"area":"offlinerl"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2310.19080","title":"Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery","created":"2023-10-29","cited_by_count":14,"area":"alignment"},{"id":"2401.08957","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","created":"2024-01-17","cited_by_count":14,"area":null},{"id":"1909.06769","title":"VILD: Variational Imitation Learning with Diverse-quality Demonstrations","created":"2019-09-15","cited_by_count":12,"area":"offlinerl"},{"id":"2405.17476","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","created":"2024-05-24","cited_by_count":12,"area":"offlinerl"},{"id":"2402.01886","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators","created":"2024-02-02","cited_by_count":11,"area":"offlinerl"},{"id":"2011.13467","title":"Episodic Self-Imitation Learning with Hindsight","created":"2020-11-26","cited_by_count":10,"area":"offlinerl"},{"id":"2110.15142","title":"Learning Feasibility to Imitate Demonstrators with Different Dynamics","created":"2021-10-28","cited_by_count":10,"area":"offlinerl"},{"id":"2201.12594","title":"Robust Imitation Learning from Corrupted Demonstrations","created":"2022-01-29","cited_by_count":10,"area":"offlinerl"},{"id":"2206.04477","title":"Receding Horizon Inverse Reinforcement Learning","created":"2022-06-09","cited_by_count":10,"area":"offlinerl"},{"id":"2210.04443","title":"Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue","created":"2022-10-10","cited_by_count":10,"area":null},{"id":"2205.04195","title":"Disturbance-Injected Robust Imitation Learning with Task Achievement","created":"2022-05-09","cited_by_count":9,"area":"offlinerl"},{"id":"2311.03485","title":"CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observations","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2008.12969","title":"Driving Through Ghosts: Behavioral Cloning with False Positives","created":"2020-08-29","cited_by_count":8,"area":"offlinerl"},{"id":"2106.14866","title":"Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits","created":"2021-06-28","cited_by_count":8,"area":null},{"id":"2209.10149","title":"Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation","created":"2022-09-21","cited_by_count":7,"area":"offlinerl"},{"id":"2402.13147","title":"SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning","created":"2024-02-20","cited_by_count":7,"area":"offlinerl"},{"id":"1907.03976","title":"Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations","created":"2019-07-09","cited_by_count":6,"area":"offlinerl"},{"id":"2312.10802","title":"GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation","created":"2023-12-17","cited_by_count":6,"area":"offlinerl"},{"id":"2104.01390","title":"No Need for Interactions: Robust Model-Based Imitation Learning using Neural ODE","created":"2021-04-03","cited_by_count":5,"area":"offlinerl"},{"id":"2110.04698","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","created":"2021-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2202.02967","title":"Learning from Imperfect Demonstrations via Adversarial Confidence Transfer","created":"2022-02-07","cited_by_count":5,"area":"offlinerl"},{"id":"2210.04303","title":"Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap","created":"2022-10-09","cited_by_count":5,"area":null},{"id":"2306.07919","title":"Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations","created":"2023-06-13","cited_by_count":5,"area":"offlinerl"},{"id":"2306.11168","title":"Learning Models of Adversarial Agent Behavior under Partial Observability","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2309.01807","title":"Marginalized Importance Sampling for Off-Environment Policy Evaluation","created":"2023-09-04","cited_by_count":5,"area":null},{"id":"2410.03626","title":"Robust Offline Imitation Learning from Diverse Auxiliary Data","created":"2024-10-04","cited_by_count":5,"area":"offlinerl"},{"id":"2107.04533","title":"Behavior Self-Organization Supports Task Inference for Continual Robot Learning","created":"2021-07-09","cited_by_count":4,"area":null},{"id":"2111.04279","title":"Batch Reinforcement Learning from Crowds","created":"2021-11-08","cited_by_count":4,"area":"offlinerl"},{"id":"2303.12375","title":"Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks","created":"2023-03-22","cited_by_count":4,"area":"offlinerl"},{"id":"2310.15815","title":"Good Better Best: Self-Motivated Imitation Learning for noisy Demonstrations","created":"2023-10-24","cited_by_count":4,"area":"offlinerl"},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2210.01379","title":"Extraneousness-Aware Imitation Learning","created":"2022-10-04","cited_by_count":3,"area":"offlinerl"},{"id":"2211.06839","title":"Out-of-Dynamics Imitation Learning from Multimodal Demonstrations","created":"2022-11-13","cited_by_count":3,"area":"offlinerl"},{"id":"2212.01343","title":"CT-DQN: Control-Tutored Deep Reinforcement Learning","created":"2022-12-02","cited_by_count":3,"area":null},{"id":"2302.06271","title":"Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning","created":"2023-02-13","cited_by_count":3,"area":"offlinerl"},{"id":"2310.07143","title":"Imitation Learning from Purified Demonstrations","created":"2023-10-11","cited_by_count":3,"area":"offlinerl"},{"id":"2311.01329","title":"A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2505.10760","title":"Counterfactual Behavior Cloning: Offline Imitation Learning from Imperfect Human Demonstrations","created":"2025-05-16","cited_by_count":3,"area":"offlinerl"},{"id":"2104.06600","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","created":"2021-04-14","cited_by_count":2,"area":"offlinerl"},{"id":"2108.00625","title":"Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning","created":"2021-08-02","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":"2210.14428","title":"D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning","created":"2022-10-26","cited_by_count":2,"area":"offlinerl"},{"id":"2211.16078","title":"Behavior Estimation from Multi-Source Data for Offline Reinforcement Learning","created":"2022-11-29","cited_by_count":2,"area":"offlinerl"},{"id":"2301.09157","title":"Immersive Demonstrations are the Key to Imitation Learning","created":"2023-01-22","cited_by_count":2,"area":"offlinerl"},{"id":"2301.11687","title":"Theoretical Analysis of Offline Imitation With Supplementary Dataset","created":"2023-01-27","cited_by_count":2,"area":"offlinerl"},{"id":"2312.05044","title":"Backward Learning for Goal-Conditioned Policies","created":"2023-12-08","cited_by_count":2,"area":null},{"id":"2404.03382","title":"DIDA: Denoised Imitation Learning based on Domain Adaptation","created":"2024-04-04","cited_by_count":2,"area":"offlinerl"},{"id":"2407.06459","title":"How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots","created":"2024-07-08","cited_by_count":2,"area":"alignment"},{"id":"2411.09953","title":"Brain-inspired Action Generation with Spiking Transformer Diffusion Policy Model","created":"2024-11-15","cited_by_count":2,"area":"diffusion"},{"id":"2503.15190","title":"Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning Approach","created":"2025-03-19","cited_by_count":2,"area":"offlinerl"},{"id":"2506.11262","title":"Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrations","created":"2025-06-12","cited_by_count":2,"area":"offlinerl"},{"id":"2602.04213","title":"InterPReT: Interactive Policy Restructuring and Training Enable Effective Imitation Learning from Laypersons","created":"2026-02-04","cited_by_count":2,"area":"offlinerl"},{"id":"2603.27944","title":"Flip Stunts on Bicycle Robots using Iterative Motion Imitation","created":"2026-03-30","cited_by_count":2,"area":"deeprl"},{"id":"2112.15221","title":"Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning","created":"2021-12-30","cited_by_count":1,"area":null},{"id":"2206.11004","title":"Auto-Encoding Adversarial Imitation Learning","created":"2022-06-22","cited_by_count":1,"area":"offlinerl"},{"id":"2212.03562","title":"Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble","created":"2022-12-07","cited_by_count":1,"area":"offlinerl"},{"id":"2406.08472","title":"RILe: Reinforced Imitation Learning","created":"2024-06-12","cited_by_count":1,"area":"offlinerl"},{"id":"2412.20193","title":"Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker","created":"2024-12-28","cited_by_count":1,"area":"offlinerl"},{"id":"2510.14467","title":"Restoring Noisy Demonstration for Imitation Learning With Diffusion Models","created":"2025-10-16","cited_by_count":1,"area":"diffusion"},{"id":"2511.07942","title":"Balance Equation-based Distributionally Robust Offline Imitation Learning","created":"2025-11-11","cited_by_count":1,"area":"offlinerl"},{"id":"2512.17899","title":"Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy","created":"2025-12-19","cited_by_count":1,"area":"offlinerl"},{"id":"2602.10793","title":"Semi-Supervised Cross-Domain Imitation Learning","created":"2026-02-11","cited_by_count":1,"area":"offlinerl"},{"id":"2101.01366","title":"A Symmetric Loss Perspective of Reliable Machine Learning","created":"2021-01-05","cited_by_count":0,"area":null},{"id":"2111.14294","title":"Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning","created":"2021-11-29","cited_by_count":0,"area":null},{"id":"2205.11019","title":"Efficient Reinforcement Learning from Demonstration Using Local Ensemble and Reparameterization with Split and Merge of Expert Policies","created":"2022-05-23","cited_by_count":0,"area":"offlinerl"},{"id":"2206.05521","title":"Model-based Offline Imitation Learning with Non-expert Data","created":"2022-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2209.04100","title":"Task-Agnostic Learning to Accomplish New Tasks","created":"2022-09-09","cited_by_count":0,"area":"offlinerl"},{"id":"2303.07846","title":"Sample-efficient Adversarial Imitation Learning","created":"2023-03-14","cited_by_count":0,"area":"offlinerl"},{"id":"2305.15193","title":"Adaptive Policy Learning to Additional Tasks","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2306.04581","title":"Divide and Repair: Using Options to Improve Performance of Imitation Learning Against Adversarial Demonstrations","created":"2023-06-07","cited_by_count":0,"area":"offlinerl"},{"id":"2411.17293","title":"SIL-RRT*: Learning Sampling Distribution through Self Imitation Learning","created":"2024-11-26","cited_by_count":0,"area":"offlinerl"},{"id":"2503.03515","title":"DO-IQS: Dynamics-Aware Offline Inverse Q-Learning for Optimal Stopping with Unknown Gain Functions","created":"2025-03-05","cited_by_count":0,"area":"deeprl"},{"id":"2505.14820","title":"Imitation Learning via Focused Satisficing","created":"2025-05-20","cited_by_count":0,"area":"offlinerl"},{"id":"2505.21182","title":"Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations","created":"2025-05-27","cited_by_count":0,"area":"offlinerl"}],"next_cursor":"100"}