Author

Liam Schramm

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Bellman Diffusion Models for Offline Reinforcement Learning

This work explores using diffusion models as a representation for the state successor measure and finds that enforcing the Bellman flow constraints on a diffusion model leads to a temporal difference update on the predicted noise, similar to the standard TD-learning update on the predicted reward.

Liam Schramm, Abdeslam Boularias · 0 citations