Skip to main content

Questions tagged [monte-carlo-tree-search]

For questions related to Monte Carlo Tree Search (MCTS), which is a best-first, rollout-based tree search algorithm. MCTS gradually improves its evaluations of nodes in the trees using (semi-)random rollouts through those nodes, focusing a larger proportion of rollouts on the parts of the tree that are the most promising.

Filter by
Sorted by
Tagged with
19 votes
3 answers
11k views

How do I choose the best algorithm for a board game like checkers?

How do I choose the best algorithm for a board game like checkers? So far, I have considered only three algorithms, namely, minimax, alpha-beta pruning, and Monte Carlo tree search (MCTS). Apparently,...
JoeyB's user avatar
  • 477
14 votes
3 answers
4k views

MCTS for non-deterministic games with very high branching factor for chance nodes

I'm trying to use a Monte Carlo Tree Search for a non-deterministic game. Apparently, one of the standard approaches is to model non-determinism using chance nodes. The problem for this game is that ...
Mark's user avatar
  • 241
15 votes
3 answers
4k views

Does Monte Carlo tree search qualify as machine learning?

To the best of my understanding, the Monte Carlo tree search (MCTS) algorithm is an alternative to minimax for searching a tree of nodes. It works by choosing a move (generally, the one with the ...
Inertial Ignorance's user avatar
10 votes
1 answer
8k views

When should Monte Carlo Tree search be chosen over MiniMax?

I would like to ask whether MCTS is usually chosen when the branching factor for the states that we have available is large and not suitable for Minimax. Also, other than MCTS simluates actions, where ...
R AND B's user avatar
  • 101
8 votes
1 answer
2k views

Any interesting ways to combine Monte Carlo tree search with the minimax algorithm?

I've been working on a game-playing engine for about half a year now, and it uses the well known algorithms. These include minimax with alpha-beta pruning, iterative deepening, transposition tables, ...
Inertial Ignorance's user avatar
7 votes
3 answers
350 views

Would AlphaGo Zero become perfect with enough training time?

Would AlphaGo Zero become theoretically perfect with enough training time? If not, what would be the limiting factor? (By perfect, I mean it always wins the game if possible, even against another ...
Christopher King's user avatar
7 votes
1 answer
657 views

When does the selection phase exactly end in MCTS?

All sources I can find provide a similar explanation to each phase. In the Selection Phase, we start at the root and choose child nodes until reaching a leaf. Once the leaf is reached (assuming the ...
Ralff's user avatar
  • 173
4 votes
1 answer
2k views

How to run a Monte Carlo Tree Search MCTS for stochastic environment?

For MCTS there is an expansion phase where we make a move and list down all the next states. But this is complicated by the fact that for some games, after making the move, there is a stochastic ...
xiaodai's user avatar
  • 141
3 votes
1 answer
248 views

AlphaGo Zero: does $Q(s_t, a)$ dominate $U(s_t, a)$ in difficult game states?

AlphaGo Zero AlphaGo Zero uses a Monte-Carlo Tree Search where the selection phase is governed by $\operatorname*{argmax}\limits_a\left( Q(s_t, a) + U(s_t, a) \right)$, where: the exploitation ...
user3667125's user avatar
  • 1,590
1 vote
1 answer
415 views

What is a policy training target in AlphaZero?

In AlphaZero's attached pseudocode, they create a training target for the policy network in this way. ...
Druudik's user avatar
  • 149