Arthur Juliani
Research Scientist at Institute for Advanced Consciousness Studies
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolArthur Juliani is a research scientist and former ML engineer with a decade of experience building and scaling reinforcement learning systems, best known for founding and developing Unity's ML-Agents toolkit used broadly to train agents in simulated 3D environments. He led teams that implemented core RL algorithms (PPO, DRQN, GAIL, ICM) in both TensorFlow and PyTorch, created the Obstacle Tower benchmark and organized its international challenge, and contributed curiosity-driven exploration and state-stacking features to open-source projects. His background blends a PhD in psychology with hands-on engineering, giving him a rare edge in designing human-inspired experiments, VR perceptual studies, and reproducible agent evaluation. After academic and industry research roles at Duke, NC State, University of Oregon, Araya, and Microsoft, he now investigates consciousness-related topics at the Institute for Advanced Consciousness Studies from his base in San Francisco.
10 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Psychology, Doctor of Philosophy (Ph.D.) Psychology at University of OregonBachelor of Arts (BA) Psychology, Bachelor of Arts (BA) Psychology at North Carolina State University
Github Skills (9)
machine-learning10
tensorflow10
mlmodel10
python10
reinforcement-learning10
ml10
unity3d9
deep-learning8
recurrent-neural-networks8
Programming languages (5)
Github contributions (5)
Unity-Technologies/ml-agents
Sep 2017 - Mar 2021
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Role in this project:
ML Engineer
ML EngineerContributions:15 releases, 49 reviews, 460 commits in 3 years 6 months
Contributions summary:Arthur primarily contributed to the implementation and enhancement of machine learning models within the Unity ML-Agents toolkit, specifically focusing on reinforcement learning algorithms like PPO and behavioral cloning. Their work included modifications to models, data structures, and training pipelines. They also addressed issues related to visual observations, and added functionality for state stacking, and curiosity-driven exploration.
deep-reinforcement-learningimitation-learningmachine-learningml-agentsreinforcement-learning
awjuliani/awjuliani.github.io
Apr 2016 - Aug 2017
Contributions:50 commits, 49 pushes, 1 branch in 1 year 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.