15 papers
Learning More from Less: Reinforcement Learning from Hindsight
Iris Xu, Sunshine Jiang, John Marangola +8
Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, but every update consumes robot rollouts that are slow and costly to collect, ma…
DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation
Martin Peticco, Gabriella Ulloa, John Marangola +2
Development of dexterous manipulation hardware has primarily focused on hands and grippers. However, these end-effectors are often paired with bulky and highly stiff wrists that li…
SoftMimic: Learning Compliant Whole-body Control from Examples
Gabriel B. Margolis, Michelle Wang, Nolan Fey +1
We introduce SoftMimic, a framework for learning compliant whole-body control policies for humanoid robots from example motions. Imitating human motions with reinforcement learning…
Robot Learning with Super-Linear Scaling
Marcel Torne, Arhan Jain, Jiayi Yuan +5
Scaling robot learning requires data collection pipelines that scale favorably with human effort. In this work, we propose Crowdsourcing and Amortizing Human Effort for Real-to-Sim…
Large Pre-Training Datasets Don't Always Guarantee Robustness after Fine-Tuning
Jaedong Hwang, Brian Cheung, Zhang-Wei Hong +3
Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of maintaining the general performance of the mo…
Language Model Personalization via Reward Factorization
Idan Shenfeld, Felix Faltings, Pulkit Agrawal +1
Modern large language models (LLMs) are optimized for human-aligned responses using Reinforcement Learning from Human Feedback (RLHF). However, existing RLHF approaches assume a un…