Ishan Durugkar
@idurugkar.bsky.social
Reinforcement learning researcher, dabbled in robotics, and generative techniques that were later made out of date by diffusion. Currently at Sony AI, working on game AI
Hey Pablo! Is this role for the Summer? I can point some folks to this great opportunity
March 20, 2025 at 2:46 PM
Hey Pablo! Is this role for the Summer? I can point some folks to this great opportunity
Oof! I can imagine. Eternally grateful that I'm working from home right now and can just take a break to go hang with the baby whenever
March 16, 2025 at 11:02 AM
Oof! I can imagine. Eternally grateful that I'm working from home right now and can just take a break to go hang with the baby whenever
This thread presents a very different viewpoint compared to my intuitions and the debate I usually see online. Looking forward to diving in!
March 15, 2025 at 3:01 PM
This thread presents a very different viewpoint compared to my intuitions and the debate I usually see online. Looking forward to diving in!
Very cool application of MARL! I'm excited to see more systems like this in the wild.
March 12, 2025 at 5:56 AM
Very cool application of MARL! I'm excited to see more systems like this in the wild.
Oof, yes. Agree with most of it too. I worry we're staring at another AI winter 😞
March 11, 2025 at 4:22 AM
Oof, yes. Agree with most of it too. I worry we're staring at another AI winter 😞
Whoa! I should try!
February 25, 2025 at 6:05 PM
Whoa! I should try!
The first part of my suggestion was kinda serious
February 25, 2025 at 5:45 PM
The first part of my suggestion was kinda serious
Maybe we should add some sort of comment section to ArXiv
Then we can have some experienced researchers who are not affiliated with the authors decide which papers have crossed the threshold to be classified as finalized papers.
Then we can have some experienced researchers who are not affiliated with the authors decide which papers have crossed the threshold to be classified as finalized papers.
February 25, 2025 at 5:40 PM
Maybe we should add some sort of comment section to ArXiv
Then we can have some experienced researchers who are not affiliated with the authors decide which papers have crossed the threshold to be classified as finalized papers.
Then we can have some experienced researchers who are not affiliated with the authors decide which papers have crossed the threshold to be classified as finalized papers.
Now we need to train a Minecraft agent that can play Atari games in there
February 13, 2025 at 2:13 PM
Now we need to train a Minecraft agent that can play Atari games in there
Haha it's so hard to keep these exciting results to yourself until you can talk about them properly! Looks like it was totally worth it though
February 8, 2025 at 2:00 AM
Haha it's so hard to keep these exciting results to yourself until you can talk about them properly! Looks like it was totally worth it though
Whoa! Very cool stuff!
February 6, 2025 at 8:52 PM
Whoa! Very cool stuff!
grad student descent is passe. Time for LLM descent!
February 1, 2025 at 6:09 PM
grad student descent is passe. Time for LLM descent!
The LLM is training us to give it a dense signal
January 25, 2025 at 5:57 AM
The LLM is training us to give it a dense signal