AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

On Strength Adjustment for MCTS-Based Programs

I-Chen Wu, Ti-Rong Wu, An-Jen Liu, Hung Guei, Tinghan Wei

AAAI 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Confounding-robust policy evaluation · 12 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 threshold ratio filter (0.1) to softmax move selectionELF OpenGo strength adjustment · GoElo range coveredImproved
use high threshold ratio (e.g. 0.5) (ablation)softmax strength adjustment · Gostrength adjustability: range smaller than 500 EloHurt
use very low threshold ratio (ablation)softmax strength adjustment · Gostrength adjustabilityHurt
use inter-game dynamic strength adjustmentELF OpenGo · Go vs opponent z=2win rate: 5.6% -> 43.4%Improved
use inter-game dynamic strength adjustmentELF OpenGo · Go vs opponent z=-2win rate: 87.6% -> 54.8%Improved
use intra-game dynamic strength adjustmentELF OpenGo · Go vs opponent z=-2win rate: 87.6% -> 71.0%Improved
use intra-game dynamic strength adjustmentELF OpenGo · Go vs opponent z=0win rate: 50.0% -> 43.0%Hurt

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