DiBB: Distributing Black-Box Optimization

no code implementations • 29 Sep 2021 • Giuseppe Cuccu, Luca Sven Rolshoven, Fabien Vorpe, Philippe Cudre-Mauroux, Tobias Glasmachers

We present a novel framework for Distributing Black-Box Optimization (DiBB).

Problem Decomposition Reinforcement Learning (RL)

NodeSketch: Highly-Efficient Graph Embeddings via Recursive Sketching

2 code implementations • ‏‏‎ ‎ 2020 • Dingqi Yang, Paolo Rosso, Bin Li, Philippe Cudre-Mauroux

Embeddings have become a key paradigm to learn graph represen-tations and facilitate downstream graph analysis tasks.

Playing Atari with Six Neurons

1 code implementation • 4 Jun 2018 • Giuseppe Cuccu, Julian Togelius, Philippe Cudre-Mauroux

Deep reinforcement learning, applied to vision-based problems like Atari games, maps pixels directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based on it.

Atari Games Decision Making +3