Mateo Guaman Castro
@mateoguaman
Followers
413
Following
2K
Media
2
Statuses
510
🤖 · 🚵♂️ · 🎸 · 🇪🇨 PhD student @uwcse working on robot learning. Previously @AirLabCMU at @CMU_Robotics. I like biking long distances and playing the bass.
Seattle, WA
Joined April 2011
RT @KuanFang: Excited to share our new work ReLIC, a framework for versatile loco-manipulation through flexible interlimb coordination. We….
0
10
0
RT @g_k_swamy: Shortcut models enable scaling offline RL, both at train-time at test-time! We beat so many other algorithms on so many task….
0
5
0
RT @sanjibac: Finally get to share one of the coolest codebases we built this past year! We combine search with learnt reward and world mod….
0
5
0
RT @g_k_swamy: Say ahoy to 𝚂𝙰𝙸𝙻𝙾𝚁⛵: a new paradigm of *learning to search* from demonstrations, enabling test-time reasoning about how to r….
0
73
0
RT @johanobandoc: 🚨 Excited to share our #ICML2025 paper: The Impact of On-Policy Parallelized Data Collection on Deep RL Networks. Big co….
arxiv.org
The use of parallel actors for data collection has been an effective technique used in reinforcement learning (RL) algorithms. The manner in which data is collected in these algorithms, controlled...
0
9
0
RT @LerrelPinto: Teaching robots to learn only from RGB human videos is hard!. In Feel The Force (FTF), we teach robots to mimic the tactil….
0
86
0
RT @haldar_siddhant: Can we teach robots to feel force without any robot data? Check out this cool work led by @AdemiAdeniji and @JoliaChen….
0
1
0
RT @Raunaqmb: Tactile feedback is key for force-aware manipulation—but collecting teleoperated data for this is difficult. Feel the Force….
0
7
0
RT @pcastr: 📢optimistic critics can empower small actors📢. new @RL_Conference paper led by my students olya and dhruv!.we study actor-criti….
0
9
0
RT @talkingrobotics: 🌟Join us next week for Talking Robotics #81 with Ravi Pandya from @ICL_at_CMU @CMU_Robotics. 🤖Title: Influence-Aware S….
0
6
0
RT @pabbeel: FastTD3: "Minimum innovation, maximum results". Not the paper we had planned to write, but one of the works I am most proud of….
0
31
0
RT @younggyoseo: Excited to present FastTD3: a simple, fast, and capable off-policy RL algorithm for humanoid control -- with an open-sourc….
0
113
0
RT @Suddhus: I'm a featured interview in our latest behind-the-scenes release! We break down the ML and perception that drives the whole-bo….
0
8
0
RT @pathak2206: Maximizing Confidence Alone Improves Reasoning. Feels like the start of the "curiosity-driven learning" era for LLMs. I hav….
0
12
0
RT @mihirp98: Excited to share our work: Maximizing Confidence Alone Improves Reasoning. Humans rely on confidence to learn when answer key….
0
35
0
RT @leggedrobotics: ANYmal just learned parkour in the wild! 9 expert skills → 1 foundation policy → RL fine-tuning → any terrain with a si….
0
11
0
RT @rdn_nikita: Happy to finally release my last PhD work, where we once again pushed the limits of what ANYmal could do. Now that the PhD….
0
7
0
RT @lchen915: One fundamental issue with RL – whether it’s for robots or LLMs – is how hard it is to get rewards. For LLM reasoning, we nee….
0
27
0