Module mcts 

Monte Carlo Tree Search (MCTS) module

This module implements the Monte Carlo Tree Search (MCTS) algorithm for making decisions in two-player perfect and hidden information games. It provides the core MCTS logic, including selection, expansion, simulation (rollout), and back-propagation phases. The MCTS algorithm builds a search tree incrementally and uses random simulations to evaluate the potential of different moves. The module is designed to be generic and works with any game state that implements the State trait, along with the ResponseGenerator and Rollout traits.

Constants

DEFAULT_EXPLORATION_CONSTANT

Default exploration constant for the UCT formula

Traits

ResponseGenerator

Response generator trait for MCTS search

Rollout

Rollout trait for MCTS search

Functions

search

Searches for the best action using the MCTS algorithm