Imitation Learning

Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling ICLR 2025 Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery ICLR 2025 Direct Repair Optimization: Training Small Language Models For Educational Program Repair Improves Feedback ACL 2025 Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning ICLR 2025 Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination ICLR 2025 Efficient Active Imitation Learning with Random Network Distillation ICLR 2025 Graph Assisted Offline-Online Deep Reinforcement Learning for Dynamic Workflow Scheduling ICLR 2025 GraphMimic: Graph-to-Graphs Generative Modeling from Videos for Policy Learning CVPR 2025 InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions CVPR 2025 Learning Strategy Representation for Imitation Learning in Multi-Agent Games AAAI 2025 ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning CVPR 2025 Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching ICLR 2025 PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning ICLR 2025 POIL:Preference Optimization for Imitation Learning ACML 2025 Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model ICLR 2025 SkillMimic: Learning Basketball Interaction Skills from Demonstrations CVPR 2025 Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation CVPR 2025 STRiDE: STate-space Riemannian Diffusion for Equivariant Planning L4DC 2025 Student-Informed Teacher Training ICLR 2025 TamedPUMA: safe and stable imitation learning with geometric fabrics L4DC 2025 VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation CVPR 2025 Watch Less, Do More: Implicit Skill Discovery for Video-Conditioned Policy ICLR 2025 What Matters in Learning from Large-Scale Datasets for Robot Manipulation ICLR 2025 When Should We Prefer State-to-Visual DAgger over Visual Reinforcement Learning? AAAI 2025 CCIL: Continuity-Based Data Augmentation for Corrective Imitation Learning ICLR 2024