AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Monte-Carlo Tree Search for Constrained POMDPs

Jongmin Lee, Geon-hyeong Kim, Pascal Poupart, Kee-Eung Kim

NeurIPS 2018 · Learning theory and algorithms › Combinatorial and search optimization · approach: Monte Carlo tree search · 30 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
use CC-POMCP (lambda-optimized scalarized tree search) instead of cost-pruning baseline MCTSPOMCP / CPOMDP solver · Rocksample (7,8)cumulative reward: -0.23 -> 9.36Improved
use CC-POMCP instead of cost-pruning baseline MCTSPOMCP / CPOMDP solver · Rocksample (11,11)cumulative reward: 0.14 -> 2.65Improved
use CC-POMCP instead of cost-pruning baseline MCTSPOMCP / CPOMDP solver · Constrained Pong, cost threshold 50cumulative reward: -20.45 -> 17.88Improved
use online CC-POMCP instead of offline CALPPOMCP / CPOMDP solver · Rocksample (7,8)cumulative reward: 3.67 -> 9.36Improved
use online CC-POMCP instead of offline CALPPOMCP / CPOMDP solver · Rocksample (5,7)cumulative reward: 12.77 -> 11.36No clear effect
tighten cost threshold from 100 to 30POMCP / CPOMDP solver · Constrained Pongcumulative reward: 19.27 -> -0.07Hurt

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