Max Sobol Mark

I am a Master’s student in Computer Science at Stanford University and a Research Assistant at IRIS Lab. The goal of my research is to develop generally capable robots that can use many skills in any new scene. I am excited to develop Reinforcement Learning methods that can take advantage of large, broad datasets that include suboptimal data.

Email  |  Resume  |  Scholar  |  Github

profile photo

Research

Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning
Jingyun Yang*, Max Sobol Mark*, Brandon Vu, Archit Sharma, Jeannette Bohg, Chelsea Finn
Preprint, under review, 2023
project page / video / arXiv
Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias
Max Sobol Mark*, Archit Sharma*, Fahim Tajwar, Rafael Rafailov, Sergey Levine, Chelsea Finn
Preprint, under review, 2023
arXiv / code
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Mitsuhiko Nakamoto*, Yuexiang Zhai*, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine
NeurIPS, 2023
project page / video / arXiv / code
Fine-tuning Offline Policies with Optimistic Action Selection
Max Sobol Mark, Ali Ghadirzadeh, Xi Chen, Chelsea Finn
NeurIPS DeepRL Workshop, 2022
Paper
Unsupervised Learning from Video with Deep Neural Embeddings
Chengxu Zhuang, Tianwei She, Alex Andonian, Max Sobol Mark, Daniel Yamins
CVPR, 2020
Paper / Code

Teaching

CS330: Deep Multi-Task and Meta Learning
Course Assistant, Stanford University, Fall 2022 and 2023
CS234: Reinforcement Learning
Course Assistant, Stanford University, Winter 2023
CS224R: Deep Reinforcement Learning
Course Assistant, Stanford University, Spring 2023

Last updated: 2024-01-07. Website template.