World Machine - Data & Report - Toy1D - Experiment 0 Protocol Test

In this World Machine experiment, our goal is to perform an initial check of whether the model is trainable using the state-discovery approach. We also assess the potential impact of the training protocol by observing the performance of trained models across the defined tasks. World Machine is a research project that investigates the concept and creation of computational world models. These AI systems create internal representations to understand and make predictions about the external world. See the project page for more information. The project is part of the H.IAAC, the Hub for Artificial Intelligence and Cognitive Architecture, located at the Universidade Estadual de Campinas (UNICAMP), Brazil. The files in this registry are organized by file extension. Each extension contains: json: metrics and logits metadata memmap: logits data pt: trained models png: plots svg: figures with experiment pipelines final_results: specific files of the final results txt: verification files