REVIEW 5 cited by
Contrastive Learning of Structured World Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). C-SWMs utilize a contrastive approach for representation learning in environments with compositional structure. We structure each state embedding as a set of object representations and their relations, modeled by a graph neural network. This allows objects to be discovered from raw pixel observations without direct supervision as part of the learning process. We evaluate C-SWMs on compositional environments involving multiple interacting objects that can be manipulated independently by an agent, simple Atari games, and a multi-object physics simulation. Our experiments demonstrate that C-SWMs can overcome limitations of models based on pixel reconstruction and outperform typical representatives of this model class in highly structured environments, while learning interpretable object-based representations.
Forward citations
Cited by 5 Pith papers
-
Learning Physics-Guided Residual Dynamics for Deformable Object Simulation
Physics-guided residual dynamics, a spring-mass simulator plus a network that predicts velocity corrections, yields the most accurate deformable-object simulation in the paper's real-world tests.
-
ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networks
A cycle-consistent GAN that translates between images and object lists matches state-of-the-art detection on synthetic scenes and detects low-contrast cells where slot-attention models fail.
-
Discovering and using Spelke segments
SpelkeNet, a self-supervised video world model, discovers Spelke segments in static images by aggregating motion correlations across imagined pokes.
-
A Definition and Roadmap for World Models
A perspective article defining world models as finite-resource compression of physical state transitions and outlining a roadmap toward physical AGI via unified representations and interactive simulators.
-
Learning Implicit Causal World Models from Multi-Agent Demonstrations
Random action noise improves multi-agent world-model OOD accuracy, but the paper's own common-cause analysis shows the causal graph contributes little at matched data.
Discussion (0). Continue with ORCID to comment.