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.
Email / Google Scholar / Twitter / GitHub / CV
Detailed C.V. (updated August 2025)
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
Selected Publications
Multi-agent
Reevaluating Policy Gradient Methods for Imperfect-Information Games
Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities
paper / code / project page
Representation learning
RL Zero: Zero-Shot Language to Behaviors without any Supervision
Robotics
Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning
Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities
paper / code / project page
Rethinking Sim2Real: Lower Fidelity Simulation Leads to Higher Sim2Real Transfer in Navigation
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.
