← Learning Types
Machine Learning › Learning Types ›

Imitation Learning

332 directly classified papers

Papers per year

Papers

SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models ICML 2023
Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior NIPS 2023
PIRLNav: Pretraining With Imitation and RL Finetuning for ObjectNav CVPR 2023
Regularized Behavior Cloning for Blocking the Leakage of Past Action Information NIPS 2023
Superhuman Fairness ICML 2023
Residual Q-Learning: Offline and Online Policy Customization without Value NIPS 2023
XSkill: Cross Embodiment Skill Discovery CORL 2023
Towards Theoretical Understanding of Inverse Reinforcement Learning ICML 2023
A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories NIPS 2023
A Coupled Flow Approach to Imitation Learning ICML 2023
Policy Contrastive Imitation Learning ICML 2023
Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts ACL 2023
Interactive Text Generation EMNLP 2023
MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations ICML 2023
TGRL: An Algorithm for Teacher Guided Reinforcement Learning ICML 2023
Coaching a Teachable Student CVPR 2023
Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal NIPS 2023
Offline Imitation Learning with Variational Counterfactual Reasoning NIPS 2023
Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation ACL 2022
An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models ACL 2022
Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning ICML 2022
Robust Imitation Learning against Variations in Environment Dynamics ICML 2022
VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator ACL 2022
Delayed Reinforcement Learning by Imitation ICML 2022
Burst-Dependent Plasticity and Dendritic Amplification Support Target-Based Learning and Hierarchical Imitation Learning ICML 2022