AlphaZero dataset. (a) Discrete-time dynamics. (b) Ranking-intensity

MuJoCo soccer dataset. (a) Discrete-time dynamics. (b)

α-Rank: Multi-Agent Evaluation by Evolution

Inverse Generative Social Science

ICLR 2022 Spotlights

HelloWorld The Big Book of Computing Content, PDF, Computer Data Storage

Cooperative and Competitive Multi-Agent Systems: From Optimization to Games-SciEngine

ICML 2021 Spotlights

A Survey on Deep Reinforcement Learning for Data Processing and Analytics

Research projects Spring 2024 - Radboud AI

α-Rank: Multi-Agent Evaluation by Evolution