AI Paper Atlas

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

VirtualHome: Simulating Household Activities via Programs

CVPR 2018 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: World-model-based agents · 374 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
Train with policy gradients using the LCS reward instead of maximum-likelihood training (ablation)Text-to-program model · VirtualHome ActivityMean LCS accuracy: .729 -> .767Helped
Add simulator executability reward to LCS reward (ablation)Text-to-program model · VirtualHome ActivityMean LCS accuracy: .767 -> .774Helped
Add simulator executability reward to LCS reward (ablation)Text-to-program model · VirtualHome ActivitySimulator executability: 35.5% -> 39.8%Helped
Train with policy gradients using the LCS reward instead of maximum-likelihood training (ablation)Video-to-program model · VirtualHome ActivityMean LCS accuracy: .478 -> .502Helped
Add simulator executability reward to LCS reward (ablation)Video-to-program model · VirtualHome ActivityMean LCS accuracy: .502 -> .495Hurt
Add simulator executability reward to LCS reward (ablation)Video-to-program model · VirtualHome ActivitySimulator executabilityHelped

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