Benchmarks for Physical Reasoning AI

1 code implementation • 17 Dec 2023 • Andrew Melnik, Robin Schiewer, Moritz Lange, Andrei Muresanu, Mozhgan Saeidi, Animesh Garg, Helge Ritter

Therefore, we aim to offer an overview of existing benchmarks and their solution approaches and propose a unified perspective for measuring the physical reasoning capacity of AI systems.

Modular Networks Prevent Catastrophic Interference in Model-Based Multi-Task Reinforcement Learning

1 code implementation • 15 Nov 2021 • Robin Schiewer, Laurenz Wiskott

As a remedy, enforcing an internal structure for the learned dynamics model by training isolated sub-networks for each task notably improves performance while using the same amount of parameters.

reinforcement-learning Reinforcement Learning +1

Latent Representation Prediction Networks

no code implementations • 20 Sep 2020 • Hlynur Davíð Hlynsson, Merlin Schüler, Robin Schiewer, Tobias Glasmachers, Laurenz Wiskott

The prediction function is used as a forward model for search on a graph in a viewpoint-matching task and the representation learned to maximize predictability is found to outperform a pre-trained representation.

Navigate