Skip to main content
Search type Search syntax
Tags [tag]
Exact "words here"
Author user:1234
user:me (yours)
Score score:3 (3+)
score:0 (none)
Answers answers:3 (3+)
answers:0 (none)
isaccepted:yes
hasaccepted:no
inquestion:1234
Views views:250
Code code:"if (foo != bar)"
Sections title:apples
body:"apples oranges"
URL url:"*.example.com"
Saves in:saves
Status closed:yes
duplicate:no
migrated:no
wiki:no
Types is:question
is:answer
Exclude -[tag]
-apples
For more details on advanced search visit our help page
Results tagged with
Search options not deleted user 1641

For questions related to game design involving AI.

4 votes
Accepted

Can you analyse a neural network to determine good states?

I don't think your network, trained using PPO to play a card game, already contains sufficient information to also use for drafting. I'm not saying this with 100% certainty, maybe there's something I' …
Dennis Soemers's user avatar
  • 10.5k
2 votes

Is it meaningful to give more weight to the result of monte carlo search with less turn win?

Traditionally (when not considering your idea), the evaluation function for terminal game states would be implemented to return $1$, $0$, or $-1$ for wins, draws, or losses, respectively. Changing th …
Dennis Soemers's user avatar
  • 10.5k
2 votes
Accepted

Is there a better way of calculating the chance of winning than $\mu * (1 - (\sigma * f)) * ...

It can make sense to incorporate the standard deviation of Monte-Carlo-based evaluations in some ways to reduce risk, but I don't think the way of using it that you described would work well. For MCT …
Dennis Soemers's user avatar
  • 10.5k
3 votes
Accepted

Which nodes are expanded in the expansion phase of MCTS?

By far the most common (and likely also the most simple / straightforward) implementation is to expand exactly one node in the Expansion Phase; specifically, the node corresponding to the very first s …
Dennis Soemers's user avatar
  • 10.5k
2 votes

How can I use a 2-dimensional feature matrix as the input to a neural network?

The most obvious way to do this would be to simply "unroll" your matrix into a vector. Your example input matrix would get turned into the following input vector: $$\left( \begin{array}{} a_1 & a_2 & …
Dennis Soemers's user avatar
  • 10.5k
8 votes
Accepted

How do I keep track of already visited states in breadth-first search?

You can use a set (in the mathematical sense of the word, i.e. a collection that cannot contain duplicates) to store states that you have already seen. The operations you'll need to be able to perform …
Dennis Soemers's user avatar
  • 10.5k
3 votes

Inconsistency in TD-Leaf algorithm in KnightCap chess engine

The second equation is correct. In TD($\lambda$), the $\lambda$ parameter can be tuned to smoothly vary between single-step updates (essentially what Sarsa does) in the case of $\lambda = 0$, and Mont …
Dennis Soemers's user avatar
  • 10.5k
3 votes
Accepted

Could you share with me the tree size, search time and search depth of your implementation o...

Intuitively I kind of doubt expecting a search depth of 10 in half a second is reasonable, especially for the initial game state where there's a rather large branching factor and no immediately-winnin …
Dennis Soemers's user avatar
  • 10.5k
2 votes

Is it feasible to use minimax to solve a board game with a large number of moves?

-The player can choose as many pieces to move as he likes. For example none, all of them, or some number inbetween. (Whereas in chess you can only move one) That quote specifically is the part th …
Dennis Soemers's user avatar
  • 10.5k
3 votes
Accepted

Connect 4 minimax does not make the best move

I suspect that you'll have to remove this code: if (field.isWinningMove(movePlayed, C4Symbol.BLUE)) { field.playMove(movePlayed, C4Symbol.RED); return new NextMove(BLUE_WIN, moveP …
Dennis Soemers's user avatar
  • 10.5k
1 vote
Accepted

MCTS with multi actions

Yes, for MCTS this is no problem at all. In fact it is slightly more annoying for minimax/alpha-beta based engines, because there we usually like (if possible) to use efficient negamax implementations …
Dennis Soemers's user avatar
  • 10.5k
5 votes
Accepted

Why does Monte Carlo work when a real opponent's behavior may not be random

First, we need to distinguish plain Monte-Carlo from Monte-Carlo Tree Search. They're different things. Monte-Carlo search, in the context of game AI search algorithms, is typically understood to me …
Dennis Soemers's user avatar
  • 10.5k
3 votes

Which value to propagate in Monte Carlo Tree Search in a non-zero-sum game?

In theory: yes, you can backpropagate any sort of scores you want to maximise. They don't have to be restricted to just a small, discrete set of values such as $\{-1, 0, 1\}$, and also do not have to …
Dennis Soemers's user avatar
  • 10.5k
5 votes
Accepted

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

There has indeed been some research towards combining MCTS and minimax-like algorithms. For example, the following two publications: Monte-Carlo Tree Search and minimax hybrids Monte-Carlo Tree Sear …
Dennis Soemers's user avatar
  • 10.5k
5 votes
Accepted

How does Hearthstone AI deal with random events

The most "standard" implementation of MCTS probably involves storing copies of game states inside nodes. This works fine for deterministic games, but not for non-deterministic games due to the reasons …
Dennis Soemers's user avatar
  • 10.5k

15 30 50 per page