Lectures related to Computer Go

Interatomic Potentials: Construction and Evaluation

Explores the construction and evaluation of interatomic potentials for atomic stability and reactivity.

Explores Monte Carlo Tree Search and Alpha Zero in deep reinforcement learning.

Deliberative Agents: Planning and Strategies

Covers planning with adversaries, heuristic search algorithms, and strategies for games with chance, emphasizing the significance of deliberative agents.

Connect Four: Alpha-Beta Pruning and Monte-Carlo Tree Search

Explores solving Connect Four using game theory algorithms and compares Alpha-Beta pruning with Monte-Carlo tree search.

Model-Based Deep RL: Planning and VAST

Covers model-based reinforcement learning, planning, variational state tabulation, and efficient Q- and V-values updating.

MuZero: Planning and Learning Model

Covers MuZero, a model that learns to predict rewards and actions iteratively, achieving state-of-the-art performance in board games and Atari video games.