DeepMind Post-Training Lead to Lecture at Oxford on Limits of Policy Gradients

DeepMind post-training lead Ian Osband will give a talk titled "The Price of Learning" at Oxford on Oct 19, arguing that policy gradients are a poor way of learning.

2026-10-12 ~ 2026-10-12 · 2 related posts

• DeepMind's Ian Osband to argue policy gradient 'can be a terrible way to learn' in Oxford talk — IanOsband · 2026-10-12
• Ian Osband to talk at Oxford on 'The Price of Learning': policy gradient can be a terrible way to learn — IanOsband · 2026-10-12