AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

POMDP Planning for Object Search in Partially Unknown Environment

Yongbo Chen, Hanna Kurniawati

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 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
add guessed target object with updating grid world (ablation)POMCP · Covered1discounted cumulative reward: 17700.2 ± 3616.6 -> 31506.9 ± 6249.7Improved
add guessed target object with updating grid world (ablation)POMCP · Loose2success rate: 65% -> 95%Improved
add guessed target object with updating grid world (ablation)POMCP · Loose1steps: 13.5 ± 6.8 -> 7.2 ± 0.7Improved
add guessed target object with updating grid world (ablation)POMCP · Covered1success rate: 65% -> 80%Improved
add guessed target object with updating grid world (ablation)POMCP · Hidden1success rate: 100% -> 100%No clear effect
use Monte Carlo update instead of Bellman update in GPOMCP (ablation)Ours_b · Hidden1discounted cumulative reward: 45038.6 ± 7631.0 -> 55574.8 ± 6225.3Improved
use Monte Carlo update instead of Bellman update in GPOMCP (ablation)Ours_b · Covered1discounted cumulative reward: 26130.6 ± 3368.7 -> 34397.8 ± 7381.6Improved
use Monte Carlo update instead of Bellman update in GPOMCP (ablation)Ours_b · Loose2discounted cumulative reward: 33265.5 ± 10085.3 -> 51574.1 ± 17930.9Improved
use Monte Carlo update instead of Bellman update in GPOMCP (ablation)Ours_b · Loose1discounted cumulative reward: 84701.5 ± 5546.8 -> 79788.0 ± 4787.4No clear effect
add belief tree reuse to POMCP_f (GPOMCP, Monte Carlo) (ablation)POMCP_f · Hidden1discounted cumulative reward: 45815.2 ± 7260.9 -> 55574.8 ± 6225.3Improved
add belief tree reuse to POMCP_f (GPOMCP, Monte Carlo) (ablation)POMCP_f · Covered1steps: 32.3 ± 6.0 -> 26.7 ± 4.8Improved
add belief tree reuse to POMCP_f (GPOMCP, Monte Carlo) (ablation)POMCP_f · Loose1discounted cumulative reward: 78629.6 ± 8472.1 -> 79788.0 ± 4787.4No 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