AI Paper Atlas

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

AGIL: Learning Attention from Human for Visuomotor Tasks

Ruohan Zhang, Zhuode Liu, Luxin Zhang, Jake A. Whritner, Karl S. Muller, Mary M. Hayhoe, Dana H. Ballard

ECCV 2018 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Theory-of-mind social reasoning · 75 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 predicted-gaze attention mask channel to the policy networkimitation policy network · MsPacman (Atari)action prediction accuracy (%): 54.6 -> 70.6Improved
add predicted-gaze attention mask channel to the policy networkimitation policy network · Seaquest (Atari)action prediction accuracy (%): 46.0 -> 61.6Improved
add predicted-gaze attention mask channel to the policy networkimitation policy network · Breakout (Atari)action prediction accuracy (%): 81.5 -> 86.2Improved
add predicted-gaze attention mask channel to the policy networkimitation policy network · Freeway and Riverraid (Atari)action prediction accuracy (%): 96.7 -> 96.4; 72.5 -> 72.5No clear effect
add foveated image channel built from ground-truth gazeimitation policy network · MsPacman (Atari)action prediction accuracy (%): 54.6 -> 65.1Improved
use attention mask instead of foveated renderingpolicy network · Seaquest (Atari)action prediction accuracy (%): 51.4 -> 61.6Improved
add AGIL attention to plain imitation learningimitation policy · Breakout (Atari game score)game score: 1.6 -> 19.9Improved
add AGIL attention to plain imitation learningimitation policy · Seaquest (Atari game score)game score: 252.2 -> 788.9Improved
add AGIL attention to plain imitation learningimitation policy · Freeway (Atari game score)game score: 29.6 -> 30.6No clear effect
add motion (optical flow) channel to the image-only gaze network (ablation)gaze network · Venture (Atari)NSS: 5.429 -> 6.222Improved
add bottom-up saliency channel to the image-only gaze network (ablation)gaze network · eight Atari gamesNSS, AUC, KL, CC: Image 6.336 vs I+S 6.363 NSS on BreakoutNo clear effect
add motion channel to image-only gaze network (ablation)gaze network · eight Atari gamesNSS, AUC, KL, CC: Image 5.776 -> I+M 5.834 NSS on SeaquestImproved

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