Search Results for author: Berkay Demirel

Found 1 papers, 0 papers with code

Speeding up reinforcement learning by combining attention and agency features

no code implementations29 Dec 2019 Berkay Demirel, Martí Sánchez-Fibla

When playing video-games we immediately detect which entity we control and we center the attention towards it to focus the learning and reduce its dimensionality.

Atari Games reinforcement-learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.