Shao ZHANG's Projects
AgentSims is an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in.
Overcooked human-AI experiment platform
A tensorflow implementation of CommunityGAN (Community Detection with Generative Adversarial Nets)
Generative Agents: Interactive Simulacra of Human Behavior
Code for "On the Utility of Learning about Humans for Human-AI Coordination"
Maximum Entropy Population Based Training for Zero-Shot Human-AI Coordination
Flexible data structures for complex machine learning datasets.
A benchmark environment for fully cooperative human-AI performance.
PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.
Python - 100ๅคฉไปๆฐๆๅฐๅคงๅธ
My academic page
Here is a system for table extraction from literature. Our models are specifivally trained at the geoscience literature, but can also process the literature from other areas.
LaTeX source and supporting code for Think Python, 2nd edition, by Allen Downey.