Ruturaj Sambhus @ruturajsambhus

PhD Student @VirginiaTech ME BTech + MTech @IITBombay CHE, ME Deep RL, MPC, Legged Locomotion, Manipulation ruturajsambhusvt.github.io Blacksburg, VA Joined December 2015

Tweets

46
Followers

49
Following

284
Likes

83

Antonin Raffin @araffin2

3 years ago

Let's try to summarize the recent advances in reinforcement learning for continuous control! Because yes, SAC and TD3 are good but there are better alternatives now ;) A small 🧵 and tentative reply to:

hardmaru @hardmaru

3 years ago

33 122 770 0 257

Download Image

6 87 473 0 303

Ching-An Cheng @ICML2025 @chinganc_rl

2 years ago

I'm looking for summer interns who are interested in RL, LLM, robotics and are open to challenge the current field. Please contact me if you're interested.

20 78 458 109K 253

IEEE Transactions on Robotics (T-RO) @IeeeTro

2 years ago

A recent T-RO paper from researchers @virginia_tech and @Caltech described an approach for real-time planning and control of two holonomically constrained quadrupedal #robots. ieeexplore.ieee.org/document/10281… #LeggedRobots #MultirobotSystems #QuadrupedalRobots

0 5 22 2K 1

Download Image

RL_Conference @RL_Conference

2 years ago

Thrilled to announce the first annual Reinforcement Learning Conference @RL_Conference, which will be held at UMass Amherst August 9-12! RLC is the first strongly peer-reviewed RL venue with proceedings, and our call for papers is now available: rl-conference.cc.

3 88 229 99K 25

Download Image

Ruturaj Sambhus @ruturajsambhus

2 years ago

Looking forward to this fun experience!

0 0 2 62 0

Pulkit Agrawal @pulkitology

2 years ago

Announcing open-source code for training locomotion controllers: github.com/Improbable-AI/… These robots run on ice, gravel, over large stones, stairs, under obstacles, on slippery surfaces, dance, recover from falls & more! Excited to see what your robots do! Led by @gabe_mrgl

6 43 249 25K 97

Download Video

K. Niranjan Kumar @kniranjankumar0

2 years ago

Excited to present this work at LangRob workshop@CoRL next month with @sehoonha @irrfaan! 🤩 🗣️💬🤖Ever thought training humanoid robots with RL is too complex? What if you could simply chat with your robot to adjust its behavior? #CoRL2023

1 5 38 4K 12

Download Gif

Nicklas Hansen @ncklashansen

2 years ago

🚨 Announcing TD-MPC2: Scalable, Robust World Models for Continuous Control TD-MPC2 performs 100+ tasks without tuning, and allows us to train a single 317M parameter model to perform 80 tasks across multiple domains, embodiments, and action spaces! nicklashansen.github.io/td-mpc2 🧵1/

4 60 279 93K 97

Download Video

Guanya Shi @GuanyaShi

2 years ago

Trajectory tracking is a standard control task, but how does a drone track arbitrary, potentially infeasible trajectories (e.g., the triangle or star shapes below) with large disturbances? Introducing Deep Adaptive Trajectory Tracking (DATT, @corl_conf'23 oral), an RL and control…

0 3 66 6K 16

Download Image

K. Niranjan Kumar @kniranjankumar0

2 years ago

Ever thought reward engineering for training humanoid robots with RL is too complex? What if you could simply chat with your robot and tell it what to do? 👤 💬 🤖 Excited to share our paper on language-based, human-guided, iterative policy learning. With @sehoonha @irrfaan

1 7 66 4K 24

Download Gif

Dhruv Batra @DhruvBatraDB

2 years ago

Announcing Habitat 3.0, simulating humanoid avatars and robots collaborating! - Humanoid sim: diverse skinned avatars - Human-in-the-loop control: mouse/keyboard or VR - Tasks: social navigation and rearrangement Over 1,000 steps per second on 1 GPU for large-scale learning!

9 87 484 261K 172

Download Video

Jim Fan @DrJimFan

2 years ago

Can GPT-4 teach a robot hand to do pen spinning tricks better than you do? I'm excited to announce Eureka, an open-ended agent that designs reward functions for robot dexterity at super-human level. It’s like Voyager in the space of a physics simulator API! Eureka bridges the…

181 1K 6K 2.7M 3K

Download Video

Antonin Raffin @araffin2

2 years ago

"Empirical Design in Reinforcement Learning" A must read for RL practitioners: arxiv.org/abs/2304.01315 (don't be intimidated by the length, you can skip to the key insights) by Andrew Patterson, Samuel Neumann, @white_martha , and Adam White.

3 35 192 17K 119

Download Image

Vikash Kumar @Vikashplus

2 years ago

Just wait until you realize that this is full-blown physics with contacts, not just a visual rendering! 💪#MuJoCo 3.0 is packed with features 👉 XLA: Accelerated physics with JAX 👉 Non-convex collisions 👉Deformable bodies Give it a try - mujoco.org/3