Computers learning Tic-Tac-Toe Pt. 3: Optimisation
Performance and hyperparameter optimisation for the vanilla DQN algorithm for Tic-Tac-Toe
Recent Posts
Computers learning Tic-Tac-Toe Pt. 2: Deep Q-learning
Learn how to make computers play Tic-Tac-Toe using deep Q-learning algorithm
Computers learning Tic-Tac-Toe Pt. 1: Tabular Q-learning
Learn how to make computers play Tic-Tac-Toe using the minimax and Q-learning algorithms
When Fourier fails: Gram-Fourier extensions
One extension to rule them all. How to efficiently reuse accurate SVD extensions.
When Fourier fails: SVDs and Fourier extensions of the third kind
Learn about the magic of high-precision extensions using SVDs.