Computers learning Bomberman Pt. 1: Tabular Q-learning
Learn how to make computers play Bomberman using the Q-learning algorithm
Learn how to make computers play Bomberman using the Q-learning algorithm
Three add-ons that stabilise and speed up deep Q-learning - Double DQN, Dueling DQN and Prioritised Experience Replay
Performance and hyperparameter optimisation for the single-network DQN algorithm for Tic-Tac-Toe
Learn how to make computers play Tic-Tac-Toe using deep Q-learning algorithm
Learn how to make computers play Tic-Tac-Toe using the minimax and Q-learning algorithms