Overview

DRLearner is an open-source project to broaden AI access and innovation by distributing AI/Machine Learning (reinforcement learning) code that rivals or exceeds human intelligence across a diverse set of widely acknowledged narrow AI benchmarks. (Within the AI research community these Arcade Learning Environment [ALE] benchmark tests are widely accepted as a proxy for agent-based intelligence.) Finally, the code is largely based on “Agent 57”, a curiosity-enhanced Deep Reinforcement Learner by Badia et al (DeepMind).

Code

Source Code:
https://github.com/PatternsandPredictions/DRLearner_beta
Dev Mailing List:
https://groups.google.com/g/drlearner/

 

Research

AGI-22: The 15th Annual AGI Conference, 19-22 August 2022 https://agi-conf.org/2022/

•  Open Source Deep Reinforcement Learning" General Interest Keynote presented by Chris Poulin (August 21, 2022)  https://drlearner.org/OpenSourceReinforcementLearning_Poulin.pdf
•  Open Source Deep Reinforcement Learning: Deep Dive" Technical presentation by co-principal author Phil Tabor. (August 22, 2022)  https://drlearner.org/DRLearner_DeepDive_Tabor.pdf
• Demo of Open Source DRLearner Tool" Code Demo by co-author Dzvinka Yarish (August 22, 2022) https://drlearner.org/DRLearner_DEMO_Yarish.pdf

Initial Announcement:
https://www.prnewswire.co.uk/news-releases/at-artificial-general-intelligence-agi-conference-drlearner-is-released-as-open-source-code-democratizing-public-access-to-state-of-the-art-software-for-ai-machine-learning-873456670.html

Team

v.01 (2022)
Chris Poulin (Project Lead)- chris@patternsandpredictions.com
Phil Tabor (Co-Lead) -ptabor@gmail.com
Dzvinka Yarish
Ostap Viniavskyi
Oleksandr Buiko
Yuriy Pryyma
Mariana Temnyk
Volodymyr Karpiv
Mykola Maksymenko
Iurii Milovanov

v.02 (2024)
Chris Poulin, Lead
Phil Tabor, Co-Lead
Damyr Hadiiev
Oleh Menchyshyn
Mateusz Kowalewski
Ihor Stets
Kateryna Lysak