ML and Game Theory

AlphaZero, CFR, multi-agent RL, GANs as games, adversarial robustness.
TUTORIALS

ML and Game Theory

AlphaZero, CFR, multi-agent RL, GANs as games, adversarial robustness.

Adversarial robustness as a game

ml-and-gt
adversarial-robustness
minimax
classification

Adversarial machine learning formulated as a two-player zero-sum game between a Defender (classifier) and an Attacker who perturbs inputs: minimax optimisation, adversarial training, and the effect on decision boundaries demonstrated with a 2D classification task.

May 8, 2026

Deep reinforcement learning for strategic games

ml-and-gt
reinforcement-learning
neural-networks
self-play

Implement simple deep RL agents from scratch in R that learn game strategies through self-play, comparing learned policies with analytical Nash equilibria.

May 8, 2026

Fictitious play and convergence

ml-and-gt
fictitious-play
learning-in-games
nash-equilibrium

Implement Brown’s fictitious play algorithm for 2x2 and 3x3 games, demonstrating convergence in zero-sum and potential games and the classic non-convergence cycling in Shapley’s counterexample.

May 8, 2026

Multi-agent reinforcement learning in matrix games

ml-and-gt
reinforcement-learning
multi-agent

Implement independent Q-learning agents that learn to play 2x2 matrix games, analyse convergence behaviour across game classes, and investigate when learning dynamics converge (or fail to converge) to Nash equilibria.

May 8, 2026

No-regret learning in games: from multiplicative weights to equilibrium

ml-and-gt
no-regret-learning
online-learning

Implement the Multiplicative Weights Update algorithm and show that when all players use no-regret learning, the time-averaged strategy profile converges to a coarse correlated equilibrium.

May 8, 2026
No matching items
Back to top