AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Sampling Networks and Aggregate Simulation for Online POMDP Planning

Hao(Jackson) Cui, Roni Khardon

NeurIPS 2019 · Reinforcement learning › MDPs and planning · approach: POMDP policy optimization · 1 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 SNAP instead of POMCP and DESPOT plannersSNAP · IPC 2011 Sysadmin, Traffic, CrossingTraffic (12 problems each)normalized cumulative rewardImproved
increase problem size (larger problem indices)SNAP vs POMCP/DESPOT · IPC 2011 domainsnormalized cumulative rewardImproved
vary planning time per step from 1 to 30 secondsSNAP vs POMCP/DESPOT · Sysadmin 10normalized scoreNo clear effect
add more sampled observations (1 to 20) (ablation)SNAP sampling networks · Sysadmin 3cumulative rewardImproved
add sampling networks for large observation spacesSNAP · Sysadmin (1045 observation variables)feasibilityImproved

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