@aspa1313

PhD student in CS at Mcgill/Mila

 Montréal, Québec
Joined February 2022
  • Tweets2
  • Following103
  • Followers30
🥳 Excited to share that our paper "Stable Deep Reinforcement Learning via Isotropic Gaussian Representations" has been accepted at #ICML2026 Spotlight (Top 2.2%)✨ 📄Paper: arxiv.org/abs/2602.19373 💻Code: github.com/asahebpa/IsoGauss… 🫶Wonderfull collaboration with @aspa1313, @AaronCourville, @PouyaBashivan and @pcastr. ✈️ See you all in Korea 🇰🇷

Stable Deep Reinforcement Learning via Isotropic Gaussian Representations

Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve over time. We show that under...

arxiv.org
Johan Obando-Ceron 👍🏽
@johanobandocMar 18
🚨 Very excited to share “Stable Deep Reinforcement Learning via Isotropic Gaussian Representations” 🎉 We show that isotropic Gaussian representations can stabilize training, prevent collapse, and reduce neuron dormancy in deep RL. A simple geometric idea with a big impact. Check out the amazing @psc thread below 👇🏽
3
12
1
100
10,507
Ali Saheb Pasand retweeted
Pablo Samuel Castro@pcastrMar 17
New paper 🚨 "Stable Deep Reinforcement Learning via Isotropic Gaussian Representations" Deep RL suffers from unstable training, representation collapse, and neuron dormancy. We show that a simple geometric insight, isotropic Gaussian representations, can fix this. Here's how 👇
4
34
4
233
26,511
Load more