TimelyDAgger: Timing-Aware Expert Querying for VLA Policy Improvement
cs.RO
Submitted: 2026-09-27
Updated: 2026-10-02
Terminology
Sources
- Human-in-the-Loop Imitation Learning using Remote Teleoperation
- EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning
- Query-Efficient Imitation Learning for End-to-End Autonomous Driving
- Uncertainty Comes for Free: Human-in-the-Loop Policies with Diffusion Models
- AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies
- Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
- Rewind-IL: Online Failure Detection and State Respawning for Imitation Learning
- CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding
- Sample-Efficient Expert Query Control in Active Imitation Learning via Conformal Prediction
- VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- OpenVLA: An Open-Source Vision-Language-Action Model
- X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving