AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Regret-Guided Search Control for Efficient Learning in AlphaZero

Yun-Jui Tsai, Wei-Yu Chen, Yan-Ru Ju, Yu-Hung Chang, Ti-Rong Wu

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add regret-guided search control (RGSC) to AlphaZeroAlphaZero · 9x9 Go vs KataGowin rate: 45.5% -> 53.6%Improved
add RGSC to AlphaZeroAlphaZero · 10x10 Othello vs Ludii alpha-betawin rate: 51.7% -> 57.8%Improved
add RGSC to AlphaZeroAlphaZero · 11x11 Hex vs MoHexwin rate: 83.6% -> 91.1%Improved
replace uniform state sampling (Go-Exploit) with regret-prioritized samplingGo-Exploit · 9x9 Go vs KataGowin rate: 49.5% -> 53.6%Improved
add RGSC when continuing training of a well-trained modelAlphaZero continued training · 9x9 Go vs KataGo (well-trained)win rate: 70.2% -> 78.2%Improved
continue training with Go-Exploit instead of AlphaZerowell-trained 9x9 Go model · 9x9 Go (well-trained)Elo: Go-Exploit performs worse than AlphaZero by 45 EloHurt
use regret ranking network instead of regret value network for state selection (ablation)RGSC · 9x9 Go, 10x10 Othello, 11x11 Hexplaying performanceImproved
rank states with regret ranking network instead of value network (ablation)RGSC · Top 2,000 selected statesaverage true regretImproved
replay high-regret states from prioritized regret bufferRGSC · 9x9 Goaverage regret: 0.655 -> 0.296Improved
raise buffer sampling probability lambda from 0.5 to 0.9 (ablation)RGSC · 11x11 Hextraining stabilityHurt
lower buffer sampling temperature tau from 1 to 0.1 (ablation)RGSC · three gamesplaying performanceImproved
increase buffer size from 100 to 500 or 1000 (ablation)RGSC · three gamesplaying performanceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy