10
Ott
18

Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents

Abstract Psychlab is a simulated psychology laboratory inside the first-person 3D game world of DeepMind Lab (Beattie et al., 2016). Psychlab enables implementations of classical laboratory psychological experiments so that they work with both human and artificial agents. Psychlab has a simple and flexible API that enables users to easily create their own tasks. As examples, we are releasing Psychlab implementations of several classical experimental paradigms including visual search, change detection, random dot motion discrimination, and multiple object tracking. We also contribute a study of the visual psychophysics of a specific state-of-the-art deep reinforcement learning agent: UNREAL (Jaderberg et al., 2016). This study leads to the surprising conclusion that UNREAL learns more quickly about larger target stimuli than it does about smaller stimuli. In turn, this insight motivates a specific improvement in the form of a simple model of foveal vision that turns out to significantly boost UNREAL’s performance, both on Psychlab tasks, and on standard DeepMind Lab tasks. By open-sourcing Psychlab we hope to facilitate a range of future such studies that simultaneously advance deep reinforcement learning and improve its links with cognitive science.

https://arxiv.org/pdf/1801.08116.pdf

DeepMind, London, UK February 6, 2018

Annunci


Time is real? I think not

ottobre: 2018
L M M G V S D
« Set   Nov »
1234567
891011121314
15161718192021
22232425262728
293031  

Commenti recenti

Inserisci il tuo indirizzo e-mail per iscriverti a questo blog e ricevere notifiche di nuovi messaggi per e-mail.

Segui assieme ad altri 1.023 follower

Latest Tweets

Annunci

%d blogger hanno fatto clic su Mi Piace per questo: