Craftax finally beaten: better prior structure beats faster simulation
GlenBerseth · x · 2026-09-30
Roger spent years trying to beat Craftax, one of the hardest RL environments, and finally won with a unique combination of Astra, input processing, and adaptive learning and memory. Key takeaway: better prior structure beats faster simulation.
More from Research
- Anima Anandkumar to Keynote SC26, Teasing a New Scaling Law Beyond LLMs — AnimaAnandkumar · 2026-09-30
- TypeSafe's Workflow Evals: decomposing policies into workflows beats prompts on accuracy, cost and speed — multiply_matrix · 2026-09-30
- SchmidhuberAI: AI proofs will be like compiler output — individual researchers' value gone in a year — ethanCaballero · 2026-09-30
- TCRvdb: a functionally validated TCR-pMHC database for specificity models — iskander · 2026-09-30
- Task Scheduling as a Bandit Problem: FLD Paper Details Continuous-Time Bandit in Human Motion Learning — breadli428 · 2026-09-30
- RoboPapers teases episode on steering pretrained robot policies with VLMs (VLS) — micoolcho · 2026-09-30