activity
20122026
most citedA Theory of Goal-Oriented MDPs with Dead Ends

45 citations · 61 across the 6 of their papers we have counts for

collaborators
Showing cs.ROShow all

5 papers · 1 filter

cs.RO2026

Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning

Patrick Yin, Tyler Westenbroek, Zhengyu Zhang +9

Reinforcement learning in massively parallel physics simulations has driven major progress in sim-to-real robot learning. However, current approaches remain brittle and task-specif…

cs.RO2026

Latent Policy Steering through One-Step Flow Policies

Hokyun Im, Andrey Kolobov, Jianlong Fu +1

Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration. Yet, offline RL's performance often hinges on a brittle trade-off betwee…

cs.RO20231 cited

Interactive Robot Learning from Verbal Correction

Huihan Liu, Alice Chen, Yuke Zhu +3

The ability to learn and refine behavior after deployment has become ever more important for robots as we design them to operate in unstructured environments like households. In th…

cs.RO2023

Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control

Vivek Myers, Andre He, Kuan Fang +7

Our goal is for robots to follow natural language instructions like "put the towel next to the microwave." But getting large amounts of labeled data, i.e. data that contains demons…

cs.RO2023

PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining

Garrett Thomas, Ching-An Cheng, Ricky Loynd +4

A rich representation is key to general robotic manipulation, but existing approaches to representation learning require large amounts of multimodal demonstrations. In this work we…