AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Maximum Entropy Monte-Carlo Planning

NeurIPS 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Determinantal point process inference · 12 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
replace UCT with MENTS (softmax backup, E2W tree policy)UCT · Atari Breakoutgame score: 367 -> 386Helped
replace UCT with MENTS (softmax backup, E2W tree policy)UCT · Atari Q*bertgame score: 16010 -> 18336Helped
replace UCT with MENTS (softmax backup, E2W tree policy)UCT · Atari SpaceInvadersgame score: 656 -> 1503Helped
replace UCT with MENTS (softmax backup, E2W tree policy)UCT · Atari BeamRidergame score: 21952 -> 18576No clear effect
replace UCT with MENTS (softmax backup, E2W tree policy)UCT · Atari Seaquestgame score: 1129 -> 1161No clear effect
replace UCT with MENTSUCT · synthetic tree, d=1 banditplanning errorHurt
replace UCT with MENTSUCT · synthetic tree, d>1 (k=8 d=5 etc.)planning errorHelped
use softmax value estimate in MENTS instead of Monte Carlo average in UCTUCT · synthetic tree value estimationvalue estimation errorHelped

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