Search Results

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' …

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 …

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 …

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 …

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 & …

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 …

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 …

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 …

-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 …

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 …

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 …

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 …

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 …

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 …

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 …