Max Rudolph

I am a PhD student at UT Austin advised by Amy Zhang working on deep reinforcement learning. I was supported by the NSF NRT Ethical AI Fellowship. I am interested in all sorts of deep reinforcement learning problems but recently I've been thinking about unsupervised learning within decision-making contexts and applying those tools to large-scale robot learning.

Previously, I did work in the Structured Techniques for Algorithmic Robotics lab (STAR) with Professor Harish Ravichandar and the Robot Autonomy and Interactive Learning lab (RAIL) with Professor Sonia Chernova. I also worked closely with Robotics PhD student Joanne Truong on sim2real for legged robotics.

Max Rudolph

Education

  • PhD in Computer Science, UT Austin, 2022 -
  • M.S. in Electrical and Computer Engineering, Georgia Institute of Technology, 2020-2021
  • B.S. in Electrical Engineering and Minor in Robotics, Georgia Institute of Technology, 2016-2020

Publications

2026

Reevaluating Policy Gradient Methods for Imperfect-Information Games

Max Rudolph*, Nathan Lichtle*, Sobhan Mohammadpour*, Alexandre Bayen, J. Zico Kolter, Amy Zhang, Gabriele Farina, Eugene Vinitsky, Samuel Sokota

ICLR 2026 RLC 2025-CoCoMARL Workshop, Oral

2025

RL Zero: Zero-Shot Language to Behaviors without any Supervision

Harshit Sikchi*, Siddhant Agarwal*, Pranaya Jajoo*, Samyak Parajuli*, Caleb Chuck*, Max Rudolph*, Peter Stone, Amy Zhang, Scott Niekum

NeurIPS 2025

2024

Learning Action-based Representations Using Invariance

Max Rudolph*, Caleb Chuck*, Kevin Black*, Misha Lvovsky, Scott Niekum, Amy Zhang

Reinforcement Learning Conference, 2024

Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning

Caleb Chuck*, Carl Qi*, Michael Joseph Munje*, Shuozhe Li*, Max Rudolph*, Chang Shi*, Siddhant Agarwal*, Harshit Sikchi*, Abhinav Peri, Sarthak Dayal, Evan Kuo, Kavan Mehta, Anthony Wang, Peter Stone, Amy Zhang, Scott Niekum

2023

Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities

Max Rudolph*, Pierce Howell*, Reza Torbati, Kevin Fu, Harish Ravichandar

Conference on Robot Learning (CoRL), 2023

2022

Rethinking Sim2Real: Lower Fidelity Simulation Leads to Higher Sim2Real Transfer in Navigation

Joanne Truong, Max Rudolph, Naoki Yokoyama, Sonia Chernova, Dhruv Batra, Akshara Rai

Conference on Robot Learning (CoRL), 2022 CoRL, 2022– Sim-to-Real Robot Learning: Locomotion and Beyond Workshop, Spotlight

2021

Desperate Times Call for Desperate Measures: Towards Risk-Adaptive Task Allocation

Max Rudolph, Sonia Chernova, Harish Ravichandar

In Proc. of The International Conference on Intelligent Robots and Systems (IROS), 2021

Range Limited Coverage Control using Air-Ground Multi-Robot Teams

Max Rudolph, Sean Wilson, Magnus Egerstedt

In Proc. of The International Conference in Robotics and Automation (ICRA), 2021.

Other stuff

I like to play tennis and make bean-to-bar chocolate and bon bons. I also run the CS Graduate Student organization (GRACS) for UTCS. During undergrad, I was lucky to intern at the National Security Agency and NASA Jet Propulsion Lab for two summers working on software for the Mars Perseverence Rover and control algorithms for the Psyche Mission.