Akshay L Chandra
@acl21.bsky.social
PhD Student at the Robot Learning Lab, University of Freiburg.
Reinforcement Learning, World Models and Robot Manipulation.
https://akshaychandra.com
Reinforcement Learning, World Models and Robot Manipulation.
https://akshaychandra.com
Hyperparameter tuning real-world policy learning by peeking into imagined rollouts inside a world model. Saved us a good few days of iterations. 😅
April 25, 2025 at 5:59 PM
Hyperparameter tuning real-world policy learning by peeking into imagined rollouts inside a world model. Saved us a good few days of iterations. 😅
TIL that dog chew toys make great robot manipulation objects. Colourful, sturdy, durable and full of grip! 🙃
March 31, 2025 at 1:52 PM
TIL that dog chew toys make great robot manipulation objects. Colourful, sturdy, durable and full of grip! 🙃
What type of classifier would you use for this data distribution? 🤔🤷♂️
February 24, 2025 at 5:28 PM
What type of classifier would you use for this data distribution? 🤔🤷♂️
In Germany, I'm obviously an Indian. In India, I'm apparently too German.
February 7, 2025 at 7:50 AM
In Germany, I'm obviously an Indian. In India, I'm apparently too German.
The owl owns my soul now. Und ich bereue nichts! 🇩🇪
February 4, 2025 at 9:04 PM
The owl owns my soul now. Und ich bereue nichts! 🇩🇪
Reposted by Akshay L Chandra
Can we extend the power of world models beyond just online model-based learning? Absolutely!
We believe the true potential of world models lies in enabling agents to reason at test time.
Introducing DINO-WM: World Models on Pre-trained Visual Features for Zero-shot Planning.
We believe the true potential of world models lies in enabling agents to reason at test time.
Introducing DINO-WM: World Models on Pre-trained Visual Features for Zero-shot Planning.
January 31, 2025 at 7:24 PM
Can we extend the power of world models beyond just online model-based learning? Absolutely!
We believe the true potential of world models lies in enabling agents to reason at test time.
Introducing DINO-WM: World Models on Pre-trained Visual Features for Zero-shot Planning.
We believe the true potential of world models lies in enabling agents to reason at test time.
Introducing DINO-WM: World Models on Pre-trained Visual Features for Zero-shot Planning.
Other than CALVIN, are there other tabletop robot manipulation sim environments with a pre-recorded play dataset? 🤔
December 31, 2024 at 1:19 PM
Other than CALVIN, are there other tabletop robot manipulation sim environments with a pre-recorded play dataset? 🤔
My IQ temporarily peaked by +200 points just by being here.
December 20, 2024 at 7:34 AM
My IQ temporarily peaked by +200 points just by being here.
Running deep RL on vectorized PyBullet envs that live and render on GPU. It is still not enough to stop our A40 cluster from sweating so much. Maybe I should take the Brax or the PufferLib route... 🤔
December 10, 2024 at 7:42 AM
Running deep RL on vectorized PyBullet envs that live and render on GPU. It is still not enough to stop our A40 cluster from sweating so much. Maybe I should take the Brax or the PufferLib route... 🤔
Reposted by Akshay L Chandra
i was recently asked to provide 4 "desert island" RL papers.
if i were stuck on a desert island i'd hope to have something better to read than #RL papers... but anyway, here's a thread with my choices, maybe you can read them on your flight to @neuripsconf.bsky.social #NeurIPS2024 .
Enjoy!
if i were stuck on a desert island i'd hope to have something better to read than #RL papers... but anyway, here's a thread with my choices, maybe you can read them on your flight to @neuripsconf.bsky.social #NeurIPS2024 .
Enjoy!
December 6, 2024 at 8:56 PM
i was recently asked to provide 4 "desert island" RL papers.
if i were stuck on a desert island i'd hope to have something better to read than #RL papers... but anyway, here's a thread with my choices, maybe you can read them on your flight to @neuripsconf.bsky.social #NeurIPS2024 .
Enjoy!
if i were stuck on a desert island i'd hope to have something better to read than #RL papers... but anyway, here's a thread with my choices, maybe you can read them on your flight to @neuripsconf.bsky.social #NeurIPS2024 .
Enjoy!
Reposted by Akshay L Chandra
A physical reasoning agent, trained on millions of problems, that you can test out by coming up with physics puzzles and seeing if it can solve them. It's fun to see if you can stump it:
kinetix-env.github.io
kinetix-env.github.io
Investigating large-scale training of RL agents in a vast and diverse space of simulated tasks
kinetix-env.github.io
November 16, 2024 at 3:29 PM
A physical reasoning agent, trained on millions of problems, that you can test out by coming up with physics puzzles and seeing if it can solve them. It's fun to see if you can stump it:
kinetix-env.github.io
kinetix-env.github.io
