Max Rudolph
@maxbrudolph
Followers
256
Following
610
Media
4
Statuses
73
CS PhD @UTAustin with @yayitsamyzhang | BS/MS @GeorgiaTech | @NSF Ethical AI Fellow. I prev RS intern @Amazon |
Atlanta
Joined July 2020
RT @agsidd10: Missed the NeurIPS deadline? RLBrew Workshop deadline in less than 15 days. Submit your finished or unfinished work to this R….
0
1
0
An incredible defense!.
Successfully defended my Ph.D. today 🎓🥳! @scottniekum and @yayitsamyzhang are the best advisors I could have ever asked for. A big thanks to my committee members @marcgbellemare @yukez @PeterStone_TX . The full presentation video will be uploaded soon. Excited about what's
0
0
2
RT @harshit_sikchi: Successfully defended my Ph.D. today 🎓🥳! @scottniekum and @yayitsamyzhang are the best advisors I could have ever aske….
0
4
0
RT @EugeneVinitsky: Hiring researchers and engineers for a stealth, applied research company with a focus on RL x foundation models. Folks….
0
35
0
In the past few days, I’ve spent way more time playing tic-tac-toe than I expected. Very cool demo from Nathan that showcases our policies.
Tic-Tac-Toe. but the opponent's moves are hidden. Can you outsmart our top RL agents? Play here:
0
0
9
We ran thousands of sweeps to compare RL algos for imperfect information games and found preliminary evidence for the Policy Gradient Hypothesis:. With proper tuning, generic PG (PPO, etc.) methods are highly competitive in IIGS. Check out the full paper:
Model-free deep RL algorithms like NFSP, PSRO, ESCHER, & R-NaD are tailor-made for games with hidden information (e.g. poker). We performed the largest-ever comparison of these algorithms. We find that they do not outperform generic policy gradient methods, such as PPO. 1/N
3
4
29
When @harshit_sikchi described this project, I knew it was going to be very cool. Is the future here?.
🤖 Introducing RL Zero 🤖: a new approach to transform language into behavior zero-shot for embodied agents without labeled datasets! RL Zero enables prompt-to-policy generation, and we believe this unlocks new capabilities in scaling up language-conditioned RL, providing an
0
0
11
RT @YuchenCui1: 🚀 I am recruiting PhD students for Fall 2025 at the UCLA Robot Intelligence Lab! 🤖 If you are interested in robot learning….
0
112
0
RT @JiahengHu1: 🚀 Despite efforts to scale up Behavior Cloning for Robots, large-scale BC has yet to live up to its promise. How can we bre….
0
37
0
RT @EugeneVinitsky: Thanks to @ben_eysenbach, this (partial) list of senior women in RL means you should never have an unbalanced panel or….
0
11
0
This work was done with with Caleb Chuck, @kvablack , Misha Lvovsky, @scottniekum , and @yayitsamyzhang . Check out the paper on arXiv….
0
1
5
If you’re in Amherst, MA for RLC 2024, come to the RLHF poster session where I’ll be presenting “Learning Action-based Representations using Invariance”. We show that you can bootstrap myopic state representations to capture features relevant to long-horizon control!. Link below!.
1
4
19
RT @agsidd10: I will be at @NeurIPSConf 2023 to present my work f-Policy Gradients (. Do check out my poster on Dec….
0
2
0
Some work from my time @GeorgiaTech on generalizing heterogeneous multi-robot policies to new team sizes, compositions and even robots! Stop by at poster session 6 @corl_conf.
🫂How to generalize heterogeneous multi-robot policies to new team sizes, composition, & even new robots?. Pierce Howell & Max Rudolph will explain how policies that account for robot capabilities can achieve this @corl_conf on Thursday (Poster 6). A 🧵 on the key ideas .
0
1
14
RT @rutavms: 🤖 Robots must understand and act upon instructions given by humans through various forms (videos, text, speech, images) to col….
0
34
0
Excited to share this work done with @joannetruong ! Very cool to work with @BostonDynamics Spot.
(1/4) Can sim2robot transfer be improved by *decreasing* simulation fidelity? .Surprisingly, yes! .Research by FAIR and @gtcomputing finds that nav policies trained with *lower* fidelity physics sim resulted in *higher* zero-shot sim2real transfer on @BostonDynamics Spot. 🧵👇
1
2
3
RT @DhruvBatraDB: Work led by @joannetruong and @maxbrudolph (at @ICatGT @mlatgt @gtcomputing), in collaboration with Naoki Yokoyama (GT),….
0
3
0
RT @GTrobotics: . @apsupdate join us at Georgia Tech for the #AtlantaScienceFest Science & Engineering Day. Activities until 2pm. #Robot Ti….
0
3
0
Check out this very cool new work by Prof. Harish Ravichandar! Very excited for this and the upcoming clean laundry!.
🚨In a new IJRR paper (, Andrew Messing & Glen Neville tackle 4 fundamental questions of multi-agent coordination *simultaneously*:.👉what (planning).👉who (allocation).👉when (scheduling).👉how (motion planning).w/ Sonia Chernova & Seth Hutchinson. 🧵👇
0
0
5
RT @DhruvBatraDB: Season 2 Episode 9 is out! . Akshara Rai (@facebookai) on Humans of AI: Stories, Not Stats. Akshara talks about the imp….
0
1
0