Jiachen Yang

Co-founder, stealth startup

Google Scholar | LinkedIn | GitHub | Email: last_name[0]+first_name@gmail.com

I pioneer the creation of autonomous agents for the long-term needs of diverse real-world applications. As a staff scientist at the Lawrence Livermore National Laboratory, I drove the advance of novel machine learning algorithms for computational science. I led the creation of agents with emergent cooperative behavior and skills to solve social dilemmas, team sports games, and multi-agent driving challenges at DeepMind, Electronic Arts, and Honda Research Institute. My main area of expertise is multi-agent deep reinforcement learning, with other publications on deep learning, meta-learning, and AI for science. I have a consistent track record of independently creating research agendas and owning projects from ideation to paper publication.

I completed a PhD in Machine Learning at the Georgia Institute of Technology, supervised by Prof. Hongyuan Zha and Prof. Tuo Zhao, with a dissertation on Cooperation in Multi-Agent Reinforcement Learning. I received an M.S. in CS from Georgia Tech and a B.S. in EECS from UC Berkeley.

Publications

Multi-Agent Reinforcement Learning for Adaptive Mesh Refinement | AAMAS 2023

Jiachen Yang, Ketan Mittal, Tarik Dzanic, Socratis Petrides, Brendan Keith, Brenden Petersen, Daniel Faissol, Robert Anderson

Reinforcement Learning for Adaptive Mesh Refinement | AISTATS 2023

Jiachen Yang, Tarik Dzanic, Brenden Petersen, Jun Kudo, Ketan Mittal, Vladimir Tomov, Jean-Sylvain Camier, Tuo Zhao, Hongyuan Zha, Tzanio Kolev, Robert Anderson, Daniel Faissol

A Unified Framework for Deep Symbolic Regression | NeurIPS 2022

Mikel Landajuela, Chak Lee, Jiachen Yang, Ruben Glatt, Claudio P. Santiago, Ignacio Aravena, Terrell N. Mundhenk, Garrett Mulcahy, Brenden K. Petersen

Adaptive Incentive Design with Multi-Agent Meta-Gradient Reinforcement Learning | AAMAS 2022

Jiachen Yang, Ethan Wang, Rakshit Trivedi, Tuo Zhao, Hongyuan Zha

Cooperation in Multi-Agent Reinforcement Learning | PhD thesis 2021

Jiachen Yang

Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach | arXiv 2021

Yan Li, Lingxiao Wang, Jiachen Yang, Ethan Wang, Zhaoran Wang, Tuo Zhao, Hongyuan Zha

Learning to Incentivize Other Learning Agents | NeurIPS 2020

Jiachen Yang, Ang Li, Mehrdad Farajtabar, Peter Sunehag, Edward Hughes, Hongyuan Zha

Graphopt: Learning optimization models of graph formation | ICML 2020

Rakshit Trivedi, Jiachen Yang, Hongyuan Zha

Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery | AAMAS 2020

Jiachen Yang, Igor Borovikov, Hongyuan Zha