AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Learning Others' Intentional Models in Multi-Agent Settings Using Interactive POMDPs

Yanlin Han, Piotr Gmytrasiewicz

NeurIPS 2018 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: World-model-based agents · 2 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
increase belief nesting level from 1 to 2I-POMDP sampling algorithm · Tiger, N=1000running time: 3.68s -> 16m36.07sHurt
increase belief nesting level from 1 to 2I-POMDP sampling algorithm · UAV, N=1000running time: 2m1.43s -> 36m19.5sHurt
increase number of samples from 500 to 2000I-POMDP sampling, level 1 · Tigerrunning time: 1.96s -> 35.2sHurt
increase number of samples from 100 to 1000I-POMDP sampling, level 1 · UAVrunning time: 4.86s -> 2m1.43sHurt
increase number of particles (ablation)I-POMDP learning · Tiger and UAVKL-divergence to ground truth parametersImproved
model the other agent with intentional I-POMDP levels instead of a subintentional frequency-based modelmodeling agent i · Tiger and UAV vs level-2 agent javerage reward per time stepImproved
use level-3 instead of level-2 modeling (ablation)modeling agent i · Tiger and UAVaverage reward per time stepNo 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