conftrace_

online imitation learning

6 papers

Explore in graph

Also known as

OIL

Co-occurring keywords · papers mentioning both

robust question answering (1) closed-loop autonomous driving (1) multi-view visual tokenizer (1) inverse soft-q learning (1) assembly (1) disassemble (1) instruction book (1) lego (1) expert-level performance (1) reward-free world models (1)

Papers

Aligning Language Models with Demonstrated Feedback ICLR 2025 DriveGPT4-V2: Harnessing Large Language Model Capabilities for Enhanced Closed-Loop Autonomous Driving CVPR 2025 Reward-free World Models for Online Imitation Learning ICML 2025 Learning to Build by Building Your Own Instructions ECCV 2024 Robust Question Answering against Distribution Shifts with Test-Time Adaption: An Empirical Study EMNLP 2022 Explaining fast improvement in online imitation learning UAI 2021