Automating the Search for Artificial Life with Foundation Models

A Kumar, C Lu, L Kirsch, Y Tang, KO Stanley… - arxiv preprint arxiv …, 2024 - arxiv.org
With the recent Nobel Prize awarded for radical advances in protein discovery, foundation
models (FMs) for exploring large combinatorial spaces promise to revolutionize many …

Learning useful representations of recurrent neural network weight matrices

V Herrmann, F Faccio, J Schmidhuber - arxiv preprint arxiv:2403.11998, 2024 - arxiv.org
Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The
program of an RNN is its weight matrix. How to learn useful representations of RNN weights …

Reinforcement learning with general evaluators and generators of policies

F Faccio - 2024 - sonar.ch
Reinforcement Learning (RL) is a subfield of Artificial Intelligence that studies how machines
can make decisions by learning from their interactions with an environment. The key aspect …

Endless minds most beautiful: building open-ended linguistic autotelic agents with deep reinforcement learning and language models

L Teodorescu - 2023 - hal.science
AI has made immense progress in the past 10 years, brought about by the increasing
availability of computation, data, and by the invention of flexible algorithmic paradigms to …

ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models

J Pourcel, C Colas, G Molinaro, PY Oudeyer… - The Thirty-eighth Annual … - openreview.net
The ability to invent novel and interesting problems is a remarkable feature of human
intelligence that drives innovation, art, and science. We propose a method that aims to …