Researchers claim Q* "solved" for 7x7 and 9x9 Go via KL-regularized critic-free RL
inductionheads · x · 2026-09-21
- Researcher yifanzhang announced that "Q has been solved", claiming a breakthrough on 7x7 and 9x9 Go, framing it as the start of the "RL scaling frontier".
- The method is KL-Regularized Policy Optimization for Critic-Free Agentic Reinforcement Learning.
- It is positioned as the culmination of a line of work including GPO, SPPO, RPG, BPO and Score Centering.
- Amplifiers expressed astonishment, but results are not yet independently verified; details are in the linked paper.
Related event: KLPO paper claims Q* solved, drawing community mockery(4 posts)→
More from Models
- OpenAI's five biggest failures laid out: pretraining decline, alignment fears, enterprise lost to Claude — teortaxesTex · 2026-11-12
- Fable 5.2 Hits 41.3% on Remote Labor Index, Up From 2.5% a Year Ago — alliekmiller · 2026-11-12
- Beaker automates MIT's weight-space programming: one-neuron edit lifts MATH-500 from 7% to 37% for under $4 — VictorSanh · 2026-11-12
- Researcher says Anthropic dodged questions on Mythos false positive rate; 37,966 findings, 2 exploited — OwariDa · 2026-11-12
- Grok spotted building meeting "Listen to Conversation" feature with live transcript — nima_owji · 2026-11-12
- MoonMath ships uncensored 763B DeepSeek-V4.1 via closed-form weight editing, claims zero capability loss — udmrzn · 2026-11-12