Multi Agent Cooperation in Game Theory
Developed based on LOLA and MCTS, the goal is to find a mechanism for the so that the agents can converge to a cooperate-cooperate equilibrium in game such as the coin game or prisoner’s dilemma game. We aim to find a scalable solution.
Tianyu Zhang
Ph.D. Student in Machine Learning
My research interests include Algorithmic Game Theory, Agent-based Model Simulator, AI for Climate Change, Multi-agent Reinforcement Learning, Self-supervised Learning, Domain Adaptation. I am still exploring and learning slowly.