←
Ishaan Javali8 posts
Ishaan Javali avatar

Ishaan Javali

@IJ_Apps

Interested in AI & startups.

◷ Joined August 2019▧ 1 Photos and videos
Ishaan Javali avatar
Ishaan Javali@IJ_Apps·27 Nov 2025

Exciting update for our paper!

Excited to share that our paper "1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities" has won the Best Paper Award at NeurIPS '25! Hope to see you all in San Diego :)

Kevin Wang avatar
⟳ Ishaan Javali retweeted
Kevin Wang@kevinwng·19 Sep 2025

Happy to share that our work “1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities” was accepted to #NeurIPS2025 as an Oral Presentation! Grateful to my amazing collaborators @IJ_Apps @m_bortkiewicz @ben_eysenbach 🥳

1/ While most RL methods use shallow MLPs (~2–5 layers), we show that scaling up to 1000-layers for contrastive RL (CRL) can significantly boost performance, ranging from doubling performance to 50x on a diverse suite of robotic tasks. Webpage+Paper+Code: wang-kevin3290.github.io/sca…

0:15
Ishaan Javali avatar
Ishaan Javali@IJ_Apps·20 Mar 2025

Check out this new paper by @kevin_wang3290, myself, @m_bortkiewicz, @tomasztrzcinsk1, and @ben_eysenbach! We show a method for scaling Contrastive RL, leading to significant performance improvements.

1/ While most RL methods use shallow MLPs (~2–5 layers), we show that scaling up to 1000-layers for contrastive RL (CRL) can significantly boost performance, ranging from doubling performance to 50x on a diverse suite of robotic tasks. Webpage+Paper+Code: wang-kevin3290.github.io/sca…

0:15
Kevin Wang avatar
⟳ Ishaan Javali retweeted
Kevin Wang@kevinwng·20 Mar 2025

1/ While most RL methods use shallow MLPs (~2–5 layers), we show that scaling up to 1000-layers for contrastive RL (CRL) can significantly boost performance, ranging from doubling performance to 50x on a diverse suite of robotic tasks. Webpage+Paper+Code: wang-kevin3290.github.io/sca…

0:15