Reinforcement-learning AIs are vulnerable to a new kind of attack

Adversarial attacks against the technique that powers game-playing AIs and could control self-driving cars shows it may be less robust than we thought.

Source : https://www.technologyreview.com/s/615299/reinforcement-learning-adversarial-attack-gaming-ai-deepmind-alphazero-selfdriving-cars/

Date : February 28, 2020 at 11:19AM

Tag(s) : Laboratoire de recherche