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

Inverse Generative Social Science

ICLR 2022 Spotlights

Frontiers AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong

4-player Kuhn poker (ranking conducted on all 256 pure strategy

ICML 2022 Spotlights

Reinforcement learning explained

Deep Reinforcement Learning Techniques in Diversified Domains: A Survey

A Complete List of All Adversarial Example Papers

Research projects Spring 2024 - Radboud AI

Aman's AI Journal • Papers List

Inverse Generative Social Science

α-Rank: Multi-Agent Evaluation by Evolution

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