{"total":17,"rows":[{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2305.14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","created":"2023-05-23","cited_by_count":20,"area":"offlinerl"},{"id":"2401.03306","title":"MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning","created":"2024-01-06","cited_by_count":14,"area":"offlinerl"},{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"area":"offlinerl"},{"id":"2403.17601","title":"LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation","created":"2024-03-26","cited_by_count":8,"area":"offlinerl"},{"id":"2407.00898","title":"Residual-MPPI: Online Policy Customization for Continuous Control","created":"2024-07-01","cited_by_count":7,"area":"offlinerl"},{"id":"2406.01793","title":"Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning","created":"2024-06-03","cited_by_count":6,"area":"offlinerl"},{"id":"2405.11139","title":"RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution Shifts","created":"2024-05-18","cited_by_count":2,"area":"offlinerl"},{"id":"2402.18617","title":"ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games","created":"2024-02-28","cited_by_count":1,"area":"offlinerl"},{"id":"2407.02245","title":"Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards","created":"2024-07-02","cited_by_count":1,"area":"offlinerl"},{"id":"2303.17010","title":"Specification-Guided Data Aggregation for Semantically Aware Imitation Learning","created":"2023-03-29","cited_by_count":0,"area":"offlinerl"},{"id":"2503.05997","title":"Learning to Drive by Imitating Surrounding Vehicles","created":"2025-03-08","cited_by_count":0,"area":"offlinerl"},{"id":"2504.14709","title":"Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline","created":"2025-04-20","cited_by_count":0,"area":"offlinerl"},{"id":"2607.17003","title":"Scalable Causal Imitation Learning","created":"2026-07-18","cited_by_count":0,"area":"offlinerl"},{"id":"2609.19894","title":"Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations","created":"2026-09-17","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"},{"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}