New MDP paper constructs learning algorithms for the bias-to-Blackwell optimality hierarchy
_onionesque · x · 2026-10-20
The arXiv paper "Towards Blackwell Optimality: Bellman Optimality Is All You Can Get" (Boone & Tuynman) studies identifying policies across the bias-optimality hierarchy up to Blackwell optimality in MDPs. For each order it constructs learning algorithms with vanishing error probability, characterizes the class of MDPs where identification can stop in finite time (those with a unique Bellman optimal policy, independent of order), and provides a tractable stopping rule.
More from Research
- Operating fully in packed space: 10k-window shuffle drops from 7.86s/8.7GB to 0.85s/0.7GB — jmschreiber91 · 2026-10-20
- Speeding up DeepLIFT/SHAP: packed-sequence dinucleotide shuffling avoids memory blowup — jmschreiber91 · 2026-10-20
- UCSB REAL AI lab hiring postdoc to build AI-driven autonomous labs — ninamiolane · 2026-10-20
- UCSB team wins $1M NSF award to study mathematical foundations of AI — ninamiolane · 2026-10-20
- Packing four loci per uint8: a memory trick that slashes DNA sequence encoding by 4x — jmschreiber91 · 2026-10-20
- Anthropic Risk Report shows distillation degrades agentic coding: SWE-bench drops detailed — maksym_andr · 2026-10-20