6 papers
When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning
Lakshita Dodeja, Ondrej Biza, Shivam Vats +5
Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning. However, BC lacks a self-guided mechanism for online improvement after demonstrations have been…
You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
Omkar Patil, Ondrej Biza, Thomas Weng +9
What happens when a pretrained generative robot policy is provided a constant initial noise as input, rather than repeatedly sampling it from a Gaussian? We demonstrate that the pe…
SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
Philip Schroeder, Thomas Weng, Karl Schmeckpeper +3
Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervise robot learning. However, when used a…
Accelerating Residual Reinforcement Learning with Uncertainty Estimation
Lakshita Dodeja, Karl Schmeckpeper, Shivam Vats +4
Residual Reinforcement Learning (RL) is a popular approach for adapting pretrained policies by learning a lightweight residual policy that provides corrective actions. While Residu…
ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
Philip Schroeder, Ondrej Biza, Thomas Weng +2
Vision-language models (VLMs) have exhibited impressive capabilities across diverse image understanding tasks, but still struggle in settings that require reasoning over extended s…
On-Robot Reinforcement Learning with Goal-Contrastive Rewards
Ondrej Biza, Thomas Weng, Lingfeng Sun +6
Reinforcement Learning (RL) has the potential to enable robots to learn from their own actions in the real world. Unfortunately, RL can be prohibitively expensive, in terms of on-r…