AI Paper Atlas

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

Learning to Play With Intrinsically-Motivated, Self-Aware Agents

Nick Haber, Damian Mrowca, Stephanie Wang, Li F Fei-Fei, Daniel L Yamins

NeurIPS 2018 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 17 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
Use the self-model policy to seek high world-model prediction loss instead of a random policy (ablation)ID-SP · Hard object interaction (one object)f accuracy: 42.1 -> 51.1Improved
Use the self-model policy to seek high world-model prediction loss instead of a random policy (ablation)ID-SP · Hard object interaction (one object)tau accuracy: 41.3 -> 43.2Improved
Use an active policy rather than a random policy (ablation)ID-SP · Object recognition transferRecognition accuracy: 12.3 -> 28.5Improved
Freeze the world-model encoding at random weights (ablation)ID-SP · Hard object interaction (one object)f accuracy: 51.1 -> 33.1Hurt
Freeze the world-model encoding at random weights (ablation)ID-SP · Hard object interaction (one object)tau accuracy: 43.2 -> 32.1Hurt
Use a latent-space future prediction world-model instead of inverse dynamics alone (ablation)self-model-driven agent · Object localization transferLocalization error [px]: 4.36 -> 5.94Hurt
Use a latent-space future prediction world-model instead of inverse dynamics alone (ablation)self-model-driven agent · Object recognition transferRecognition accuracy: 28.5 -> 18.7Hurt
Train with two objects present instead of one (ablation)ID-SP · Recognition transferRecognition accuracy: 28.5 -> 39.7Improved
Increase the ID-SP policy horizon to T=40 rather than use a shorter horizon such as T=5 (ablation)ID-SP · Two-object interactionstwo-object play state frequencyImproved
Use LF-SP rather than ID-SP with a long horizon for multi-object play (ablation)self-model-driven agent · Two-object interactionstwo-object play state frequencyHurt

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