Akshay L Chandra

Robot Learning: Generalization In Planning YouTube video by Montreal Robotics

Thank you for the amazing lecture series. I think the above link is broken or points to a private video.

This maybe the right link: youtu.be/S-LgYX5qETo

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! 🙃

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.

The owl owns my soul now. Und ich bereue nichts! 🇩🇪

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.

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.

I am literally the only one using the cluster at the moment. 🫠

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... 🤔

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!

My CPU is handling my master's thesis better than I am. Respect! #MBRL

I just read your last two posts and skimmed through the respective papers (BBF and ReDo), it's around 06:30 where I live and I already feel like I had a productive day. I could just go back to bed with no guilt whatsoever. 😅

Thank you for sharing! ✌🏽

Investigating large-scale training of RL agents in a vast and diverse space of simulated tasks

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

The end is opener too. ;)

If robots can't handle a rave, what's even the point of all this? 😅

I thought the LED inside the oven was a nice touch. I collected hours of play data with it.

Should I now be worried about the Amazon seller no more selling the LED? 🥲

#RL #Robotics

I'm a graduate student working in RL + Robotics. I'd like to be added please. :)

Very new to this platform. I work with robot manipulators everyday at Uni-Freiburg.

I would really appreciate you adding me to the group. :)