AI & ML
Old Experience, New Lessons: Relabeling Autonomous Robot Rollouts in Interactive Imitation Learning
arXiv cs.RO0 views
arXiv:2611.24273v1 Announce Type: new Abstract: Interactive imitation learning enables robots to learn from human interventions during deployment. These interactions naturally produce sparse human corrections and abundant autonomous robot experience without human action labels. Yet existing methods either leave this experience unused for action supervision or imitate historical robot actions, which can reinforce suboptimal behavior. To address this limitation, we propose Set-valued Relabeling of Autonomous experience (SeRA), a framework that learns from autonomous robot experience through set-valued supervision of policy relabels. Later policy checkpoints relabel this experience, and agreement across checkpoints filters the relabels. Since agreement does not guarantee correctness, SeRA constructs desired action sets around accepted relabels. Following Set-Supervised Diffusion Policy (SDP), it trains an action-chunking diffusion policy to increase the probability of actions within these sets. A step-masked denoising loss combines accepted relabels with available human corrections in partially supervised chunks. Experiments across five simulated manipulation tasks in online and offline settings show that SeRA improves policy performance over SDP and outperforms baselines that imitate historical robot actions or exact relabels. On a real-robot tomato-picking task, SeRA achieves 80% success, compared with 40% for SDP, using the same human feedback and training budget. These results demonstrate that relabeled autonomous robot experience can complement human corrections to improve policy performance.
Source:https://arxiv.org/abs/2611.24273PreviousTowards Vacuum-Assisted Robotic Needle Interventions: From Fluid Aspiration to Tissue BiopsyNextQDD-MM: A Simple and Compact Open-Source Muscle Module with Quasi-Direct-Drive Motor for Tendon-driven Robots
Related posts
Your AI Coding Limits Ran Out Early? Find What Is Burning Them
0dev.to
Frontier Models Are Smarter Than Ever — So Why Do You Still Need a Swarm Harness Like VibesPlug?
0dev.to
Ruby2ßhell: Pre-authentication RCE on stock Rails
0Hacker News
Generalizing self-normalized importance sampling with couplings
0arXiv stat.CO
Bayesian Computation of Copula-based Multivariate Models with an Application to Doping Detection
0arXiv stat.CO
WAIVES: Weak-form Asymptotically-unbiased Instrumental-Variable Estimation for SDEs
0arXiv stat.CO