Announcement_8

Created on November 05, 2026

2026

Our paper D²-OPD: Separating Direction and Distance in Extrapolative On-Policy Distillation is now on arXiv! This work from my Amazon AGI internship improves language-model distillation by separating where to extrapolate from how far to move.

Enjoy Reading This Article?

Here are some more articles you might like to read next:

Some Recent Advancement Around MuZero

MPC with a Differentiable Forward Model: An Implementation with Jax

Adding MuZero into RL Toolkits at Ease

“Hindsight” – An easy yet effective RL Technique HER with Pytorch implementation

What are the Effective Deep Learning Models for Tabular Data?