AI Paper Atlas

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

HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks

Zhou Xian, Shamit Lal, Hsiao-Yu Tung, Emmanouil Antonios Platanios, Katerina Fragkiadaki

ICLR 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Imitation and skill learning · 3 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
Generate system-conditioned dynamics experts instead of using a fixed global modelHyperDynamics vs. Direct · Object pushingprediction errorImproved
Generate system-conditioned dynamics experts instead of using a fixed global modelHyperDynamics vs. Direct · Object pushingsuccess rateImproved
Infer system properties and generate an expert for unseen objectsHyperDynamics vs. XYZ · Unseen object pushingsuccess rateImproved
Generate dynamics directly from inferred properties rather than adapt parameters with gradient stepsHyperDynamics vs. MB-MAML · Object pushing with 5 interaction samplesprediction errorImproved
Generate system-conditioned dynamics expertsHyperDynamics vs. Recurrent and MB-MAML · Locomotionaverage returnImproved
Generate system-conditioned dynamics expertsHyperDynamics vs. Recurrent and MB-MAML · Locomotion prediction errormean squared errorImproved
Add top-down shape reconstruction to regularize training (ablation)HyperDynamics for object pushing · Object pushingprediction errorImproved
Crop the scene feature map to produce object-centric features (ablation)HyperDynamics for object pushing · Object pushingprediction errorImproved
Use detected rather than ground-truth object positions (ablation)HyperDynamics for object pushing · Object pushingprediction errorHurt
Increase the visual latent code dimension beyond the chosen size (ablation)HyperDynamics for object pushing · Object pushingprediction errorNo clear effect
Increase the interaction latent code dimension beyond the chosen size (ablation)HyperDynamics · Object pushing and locomotionprediction errorNo 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