{"total":56,"rows":[{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260,"area":"offlinerl"},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134,"area":"offlinerl"},{"id":"1901.09387","title":"Imitation Learning from Imperfect Demonstration","created":"2019-01-27","cited_by_count":114,"area":"offlinerl"},{"id":"1807.08364","title":"EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning","created":"2018-07-22","cited_by_count":100,"area":"offlinerl"},{"id":"1807.09936","title":"Multi-Agent Generative Adversarial Imitation Learning","created":"2018-07-26","cited_by_count":100,"area":"offlinerl"},{"id":"1812.04155","title":"Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention","created":"2018-12-10","cited_by_count":77,"area":"offlinerl"},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73,"area":"offlinerl"},{"id":"1907.13220","title":"Multi-Agent Adversarial Inverse Reinforcement Learning","created":"2019-07-30","cited_by_count":60,"area":"offlinerl"},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"1909.09314","title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","created":"2019-09-20","cited_by_count":50,"area":"offlinerl"},{"id":"2107.08829","title":"Visual Adversarial Imitation Learning using Variational Models","created":"2021-07-16","cited_by_count":42,"area":"offlinerl"},{"id":"1805.12573","title":"Learning a Prior over Intent via Meta-Inverse Reinforcement Learning","created":"2018-05-31","cited_by_count":36,"area":"offlinerl"},{"id":"1909.05477","title":"Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning","created":"2019-09-12","cited_by_count":34,"area":"offlinerl"},{"id":"2207.08645","title":"Active Exploration for Inverse Reinforcement Learning","created":"2022-07-18","cited_by_count":27,"area":"offlinerl"},{"id":"1901.02161","title":"Risk-Aware Active Inverse Reinforcement Learning","created":"2019-01-08","cited_by_count":26,"area":"offlinerl"},{"id":"2106.00099","title":"Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs","created":"2021-05-31","cited_by_count":22,"area":"offlinerl"},{"id":"2209.10974","title":"Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning","created":"2022-09-22","cited_by_count":16,"area":"offlinerl"},{"id":"1806.03820","title":"An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning","created":"2018-06-11","cited_by_count":15,"area":"offlinerl"},{"id":"2109.04307","title":"OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching","created":"2021-09-09","cited_by_count":15,"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":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2202.06003","title":"Robust Learning from Observation with Model Misspecification","created":"2022-02-12","cited_by_count":9,"area":"offlinerl"},{"id":"2204.09772","title":"A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines","created":"2022-04-20","cited_by_count":9,"area":"offlinerl"},{"id":"1907.13627","title":"Disentangled Relational Representations for Explaining and Learning from Demonstration","created":"2019-07-31","cited_by_count":8,"area":"offlinerl"},{"id":"2109.11018","title":"Making Human-Like Trade-offs in Constrained Environments by Learning from Demonstrations","created":"2021-09-22","cited_by_count":7,"area":"offlinerl"},{"id":"2310.12055","title":"Understanding Reward Ambiguity Through Optimal Transport Theory in Inverse Reinforcement Learning","created":"2023-10-18","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":"2012.02527","title":"Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments","created":"2020-12-04","cited_by_count":6,"area":"offlinerl"},{"id":"2604.14265","title":"Reinforcement Learning via Value Gradient Flow","created":"2026-04-15","cited_by_count":5,"area":"offlinerl"},{"id":"2411.15046","title":"On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning","created":"2024-11-22","cited_by_count":4,"area":"offlinerl"},{"id":"2002.09043","title":"oIRL: Robust Adversarial Inverse Reinforcement Learning with Temporally Extended Actions","created":"2020-02-20","cited_by_count":3,"area":"offlinerl"},{"id":"2204.05909","title":"Learning Performance Graphs from Demonstrations via Task-Based Evaluations","created":"2022-04-12","cited_by_count":3,"area":"offlinerl"},{"id":"2211.15339","title":"Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning","created":"2022-11-24","cited_by_count":3,"area":"offlinerl"},{"id":"2302.06271","title":"Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning","created":"2023-02-13","cited_by_count":3,"area":"offlinerl"},{"id":"2308.07598","title":"Generating Personas for Games with Multimodal Adversarial Imitation Learning","created":"2023-08-15","cited_by_count":3,"area":"offlinerl"},{"id":"2309.14003","title":"Hierarchical Imitation Learning for Stochastic Environments","created":"2023-09-25","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":"2410.23680","title":"Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment","created":"2024-10-31","cited_by_count":3,"area":"offlinerl"},{"id":"2407.19902","title":"A Differential Dynamic Programming Framework for Inverse Reinforcement Learning","created":"2024-07-29","cited_by_count":2,"area":"offlinerl"},{"id":"2507.22640","title":"Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction","created":"2025-07-30","cited_by_count":2,"area":"offlinerl"},{"id":"2509.03790","title":"What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?","created":"2025-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"1903.05697","title":"Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks","created":"2019-03-13","cited_by_count":1,"area":"offlinerl"},{"id":"2106.05535","title":"Differentiable Robust LQR Layers","created":"2021-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2202.07014","title":"Strategy Discovery and Mixture in Lifelong Learning from Heterogeneous Demonstration","created":"2022-02-14","cited_by_count":1,"area":"offlinerl"},{"id":"2505.21639","title":"Apprenticeship learning with prior beliefs using inverse optimization","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2510.17059","title":"Consistent Zero-Shot Imitation with Contrastive Goal Inference","created":"2025-10-20","cited_by_count":1,"area":"offlinerl"},{"id":"1912.08444","title":"Relational Mimic for Visual Adversarial Imitation Learning","created":"2019-12-18","cited_by_count":0,"area":"offlinerl"},{"id":"2306.01731","title":"PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial Reward","created":"2023-06-02","cited_by_count":0,"area":"offlinerl"},{"id":"2502.20089","title":"RIZE: Adaptive Regularization for Imitation Learning","created":"2025-02-27","cited_by_count":0,"area":"offlinerl"},{"id":"2505.14820","title":"Imitation Learning via Focused Satisficing","created":"2025-05-20","cited_by_count":0,"area":"offlinerl"},{"id":"2507.08707","title":"SPLASH! Sample-efficient Preference-based inverse reinforcement learning for Long-horizon Adversarial tasks from Suboptimal Hierarchical demonstrations","created":"2025-07-11","cited_by_count":0,"area":"offlinerl"},{"id":"2509.08257","title":"Symmetry-Guided Multi-Agent Inverse Reinforcement Learning","created":"2025-09-10","cited_by_count":0,"area":"offlinerl"},{"id":"2511.20992","title":"Dataset Poisoning Attacks on Behavioral Cloning Policies","created":"2025-11-26","cited_by_count":0,"area":"offlinerl"},{"id":"2605.09818","title":"Learning to Compress Time-to-Control: A Reinforcement Learning Framework for Chronic Disease Management","created":"2026-05-10","cited_by_count":0,"area":"offlinerl"},{"id":"2607.17760","title":"Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning","created":"2026-07-20","cited_by_count":0,"area":"offlinerl"},{"id":"2610.10601","title":"Teaching a Robot Dog New Tricks: Diverse Quadruped Skills via Combined Reinforcement and Imitation Learning with Adversarial Task Selection","created":"2026-10-06","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}