AI Paper Atlas

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

Ask4Help: Learning to Leverage an Expert for Embodied Tasks

Kunal Pratap Singh, Luca Weihs, Alvaro Herrasti, Jonghyun Choi, Aniruddha Kembhavi, Roozbeh Mottaghi

NeurIPS 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 5 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 a learned policy that requests expert actions when usefulEmbCLIP on RoboTHOR ObjectNav · RoboTHOR ObjectNav validationsuccess rate: 52.4 -> 86.3Improved
Use human experts to provide requested actionsAsk4Help on RoboTHOR ObjectNav · RoboTHOR ObjectNav validationsuccess rate: 55.7 -> 81.6Improved
Use a corrupted expert with epsilon 0.8Ask4Help on RoboTHOR ObjectNav · RoboTHOR ObjectNav validationsuccess rate: 52.4 -> 67.1Improved
Add learned help requests rather than use no expertEmbCLIP on iTHOR RoomR · iTHOR RoomR validationsuccess rate (%): 6.90 -> 90.4Improved
Use learned requests instead of Model Confusion 0.3EmbCLIP on iTHOR RoomR · iTHOR RoomR validationsuccess rate (%): 89.9 -> 90.4Improved
Train Ask4Help with 10% rather than 25% of training scenes (ablation)Ask4Help on RoboTHOR ObjectNav · RoboTHOR ObjectNav validationsuccess rate: 2% dropHurt
Train Ask4Help with 10% rather than 25% of training scenes (ablation)Ask4Help on RoboTHOR ObjectNav · RoboTHOR ObjectNav validationSPL: 1%Hurt
Replace the pre-trained navigation agent with a random agent (ablation)Ask4Help on RoboTHOR ObjectNav · RoboTHOR ObjectNav validationsuccess rate: 86.3 -> 76.44Hurt
Replace the pre-trained navigation agent with a random agent (ablation)Ask4Help on RoboTHOR ObjectNav · RoboTHOR ObjectNav validationexpert proportion (%): 12.31 -> 98.99Hurt
Limit expert availability to 20 steps per episodeAsk4Help versus Model Confusion on RoboTHOR ObjectNav · RoboTHOR ObjectNav validationsuccess rate: 61% -> 70%Improved

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