
TL;DR
Neural NID introduces a graph neural network-based approach inspired by NID rules to learn and generalize object properties and relations, improving transition dynamics prediction in model-based reinforcement learning.
Contribution
It presents Neural NID, a novel method combining NID rules with graph neural networks for better generalization in learning object dynamics.
Findings
Neural NID outperforms standard models on benchmark tasks.
It demonstrates improved generalization to novel situations.
The approach effectively captures object relations and properties.
Abstract
Abstract object properties and their relations are deeply rooted in human common sense, allowing people to predict the dynamics of the world even in situations that are novel but governed by familiar laws of physics. Standard machine learning models in model-based reinforcement learning are inadequate to generalize in this way. Inspired by the classic framework of noisy indeterministic deictic (NID) rules, we introduce here Neural NID, a method that learns abstract object properties and relations between objects with a suitably regularized graph neural network. We validate the greater generalization capability of Neural NID on simple benchmarks specifically designed to assess the transition dynamics learned by the model.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Applications · Reinforcement Learning in Robotics · Evolutionary Algorithms and Applications
