This is a Java implementation of Monte Carlo Tree Search methods. It is self-contained, domain-independent and can thus easily be used in any state-action domain. The project was developed for the purpose of my Bachelor’s thesis.
JUnit4, Java cloning library
Create the implementation of MctsDomainAgent.
public class Player implements MctsDomainAgent<State> {...}Create the implementation of MctsDomainState.
public class State implements MctsDomainState<Action, Player> {...}Initialize the search and invoke uctSearchWithExploration() to get the most promising action.
Mcts<State, Action, Player> mcts = Mcts.initializeIterations(NUMBER_OF_ITERATIONS);
Action mostPromisingAction = mcts.uctSearchWithExploration(state, explorationParameter);For algorithm to work correctly it is necessary that state's method getAvailableActionsForCurrentAgent() either returns the same instances of objects or returns objects that override equals() and hashCode() methods.
Before every tree expansion and simulation a deep clone of represented state is created. This can lead to performance issues and should be taken into account when implementing MctsDomainState. You can optionally set which classes should be ignored during state cloning.
mcts.dontClone(DontCloneMe0.class, DontCloneMe1.class, ...);Tic-Tac-Toe example can be found in the test directory and Scotland Yard board game example can be found here.
This project is licensed under the terms of the MIT license. See LICENSE.md.
Nejc Ilenič