Aditya Bhatt (@aditya_bhatt) 's Twitter Profile
Aditya Bhatt

@aditya_bhatt

PhD student (DFKI / IAS / TU Darmstadt) in Robotics 🤖 researching dexterous manipulation with
flexible robots 🦾 weird control 🪁 Deep RL 🧠

[email protected]

ID: 43854667

linkhttp://aditya.bhatts.org calendar_today01-06-2009 08:41:29

453 Tweet

969 Takipçi

1,1K Takip Edilen

Aditya Bhatt (@aditya_bhatt) 's Twitter Profile Photo

One more thing: In a 100% empirical side-quest, we found a surprising alternative to target nets: Bounded activations permit stable, divergence-free training! 😂 Feature normalizers like LayerNorm, BatchNorm, etc. also permit this, *with* unbounded activations like ReLU! 😆

One more thing:
In a 100% empirical side-quest, we found a surprising alternative to target nets: 

Bounded activations permit stable, divergence-free training! 😂

Feature normalizers like LayerNorm, BatchNorm, etc. also permit this, *with* unbounded activations like ReLU! 😆
Georgia Chalvatzaki (@georgiachal) 's Twitter Profile Photo

Honored to give an Early Career Keynote at #CoRL2024! My talk, "On the Quest for Robotic Embodied Intelligence," will explore how structure in robot learning enables faster, safer, and adaptive robot behaviors. Excited to share this vision! 🚀 corl.org/program/speake… #robotics

Honored to give an Early Career Keynote at #CoRL2024!  My talk, "On the Quest for Robotic Embodied Intelligence," will explore how structure in robot learning enables faster, safer, and adaptive robot behaviors. Excited to share this vision! 🚀 
 corl.org/program/speake… #robotics
Daniel Palenicek (@dpalenicek) 's Twitter Profile Photo

Check out our latest work, where we train an omnidirectional locomotion policy directly on a real quadruped robot in just a few minutes based on our CrossQ RL algorithm 🚀 Shoutout to Nico Bohlinger, Jonathan Kinzel and MAB Robotics. Intelligent Autonomous Systems Group Computer Science, TU Darmstadt hessian.AI

Aditya Bhatt (@aditya_bhatt) 's Twitter Profile Photo

CrossQ can learn quadrupedal walking in minutes! Use it as a lightweight replacement for SAC, and train faster in fewer gradient steps!

Firas Al-Hafez (@firasalhafez) 's Twitter Profile Photo

🚀 We’re releasing #LocoMuJoCo2 — An extensive library for whole-body imitation & RL. 🔥 Highlights: - Supports MuJoCo & MJX - Clean JAX impl of PPO, GAIL, AMP, DeepMimic - 22K+ trajectories per humanoid - Add your humanoid easily 🔗 github.com/robfiras/loco-… 🧵Details 👇