{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/psychlab-a-psychology-laboratory-for-deep","title":"Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents","arxiv_id":"1801.08116","date":"2018-01-24","proceeding":null,"authors":["Joel Z. Leibo","Cyprien de Masson d'Autume","Daniel Zoran","David Amos","Charles Beattie","Keith Anderson","Antonio García Castañeda","Manuel Sanchez","Simon Green","Audrunas Gruslys","Shane Legg","Demis Hassabis","Matthew M. Botvinick"],"abstract":"Psychlab is a simulated psychology laboratory inside the first-person 3D game\nworld of DeepMind Lab (Beattie et al. 2016). Psychlab enables implementations\nof classical laboratory psychological experiments so that they work with both\nhuman and artificial agents. Psychlab has a simple and flexible API that\nenables users to easily create their own tasks. As examples, we are releasing\nPsychlab implementations of several classical experimental paradigms including\nvisual search, change detection, random dot motion discrimination, and multiple\nobject tracking. We also contribute a study of the visual psychophysics of a\nspecific state-of-the-art deep reinforcement learning agent: UNREAL (Jaderberg\net al. 2016). This study leads to the surprising conclusion that UNREAL learns\nmore quickly about larger target stimuli than it does about smaller stimuli. In\nturn, this insight motivates a specific improvement in the form of a simple\nmodel of foveal vision that turns out to significantly boost UNREAL's\nperformance, both on Psychlab tasks, and on standard DeepMind Lab tasks. By\nopen-sourcing Psychlab we hope to facilitate a range of future such studies\nthat simultaneously advance deep reinforcement learning and improve its links\nwith cognitive science.","url_abs":"http://arxiv.org/abs/1801.08116v2","url_pdf":"http://arxiv.org/pdf/1801.08116v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"psychlab-a-psychology-laboratory-for-deep","repo_url":"https://github.com/susumuota/gym-oculoenv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"change-detection","task_name":"Change Detection"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.08116","atlas_url":"https://app.syntology.ai/?focus=1801.08116","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}