Ian Osband to talk at Oxford on 'The Price of Learning': policy gradient can be a terrible way to learn
IanOsband · x · 2026-10-12
DeepMind researcher Ian Osband will give a talk titled 'The Price of Learning' at Oxford Maths on Monday, October 19 at 2pm. His thesis: policy gradient drives modern LLM post-training, but it can be a terrible way to learn. The talk is open to attend, and he jokingly invited colleagues from related labs to join for the day.
More from Research
- Graph algorithm researchers shrug at OpenAI's general matching math result — thegautamkamath · 2026-10-13
- STOKE: Stanford's superoptimizer finds optimal assembly through randomness with early pruning — lauriewired · 2026-10-13
- Muse Wonder Full beats its scaling trend on out-of-distribution tasks, Meta says — AIatMeta · 2026-10-13
- ReplaySSM ships in GLM-5.3-Flash and Kimi-K3, speeding decoding up to 2.1x — tri_dao · 2026-10-13
- DeepRSI benchmark pushes agents to 48-hour ML tasks to measure recursive self-improvement — garrytan · 2026-10-13
- Datalab launches OmniParseBench, a game-resistant OCR benchmark where it doesn't rank first — VikParuchuri · 2026-10-13