Hot answers tagged

5

Humans VS machines in the 60s-70s: one way of putting this accomplishment in perspective is by regarding the results of the match between Bobby Fischer and MIT Greenblatt computer program (Running Mac-Hack, a software written by the great Richard Greenblatt himself) in 1977. I do believe that in 1977, Fisher was still very representative of what humans can ...


4

This idea was very popular back in the days, some programmers used their best to create such engines, and they did achieve that (to a certain extend) Some engines that you might want to check out are: Rebel ProDeo ShashChess Szint Szint has more of 100 personalities classified in 3 forms. Szint Training with personalities from 0 to 2600 of elo. Szint GM with ...


3

If you do not want to use a library/API to get this information, then you will need to implement some parsing to get it, but in principle (almost) all the info you need is available via (non-standard) UCI commands: Legal moves Perft lists all legal moves. E.g., for the starting position go perft 1 gives you: a2a3: 1 b2b3: 1 c2c3: 1 d2d3: 1 e2e3: 1 f2f3: 1 ...


3

There are few engines that are capable of such thing. One name that I can recall is the old Spark UCI engine by Allard Siemelink. Very aggressive engine with twistable attacking parameters. It has a feature called MultiPVMargin which enables you to set certain number difference between the PV (Principle Variations) measured in centipawn. For example if your ...


2

Not long ago I was looking for very similar thing, the closest I got was program called ChessTricks. The program is using a chess UCI engine to analyse different positions with the sole purpose of looking for traps and tricks. Let's say for example that you are playing a game against the computer and you find yourself in a position where the computer is ...


2

I took a peek at the code given in a comment. It seems to have a small semi-random factor added to the evaluation, probably so it can more easily just pick a move from all the ties that are going to come up. However, the size of the score difference appears to be greater than what could be explained by just this. Also, at move 65 it evaluates the position as ...


2

This is a very interesting question. Yes I think are people that have tried to implement a "style" of a player, but most engines use a minimax algorithm also know as alpha-beta pruning. However, if you take a look at machine learning models, like Alpha Go, they first emulate/learn for a training set from the masters (called prior) and then train ...


2

For most such questions perhaps a chess problem engine like Popeye can easily solve it. However, the kind of goals your question is indicating like extinction of opponent pieces can also be set in configurable chess variant engines, e.g., Fairy-Stockfish or Sjaak II. I would assume that in most cases this will be the easier and faster solution, assuming that ...


1

I think this type of thing can be achieved using chess engines to certain degree. I am afraid this is not possible with machine learning because of the nature of reinforced learning (Andrew's idea is creative; but I don't think it will work that way). Some aspects of a player's style can be mimicked by forcing a usual chess engine to choose certain types of ...


1

Chess.com semi recently added bots that play like different people in real life. There aren’t a ton of people but it does have a few. A wider range of different players is supported by the engine used in the unfortunately discontinued Chessmaster games by Ubisoft. https://en.wikipedia.org/wiki/Chessmaster I’m not the biggest expert in famous players and ...


1

In the GUI Nibbler you have a setting called "Temperature". The higher the temperature value, the more it allows the engine to play unexpected moves. You can also set temperature decay to X moves, so that after X moves it starts playing best moves again. You can load any engine you want in Nibbler, but it is designed for NN engines, such as Lc0.


1

Obviously, there is no such thing for you to download. If you want to happen, you need to do the works. It's not hard. Run engine analysis on multi-pv mode Check engine score for each line. Play the move according to your rules.


1

There are other anomalies too, like around move 14 or so (though these may be rounding errors?). Do you have SimpleEval's code to be sure that it is only counting material. One possible explanation (though not relevant in this case) is that sometimes a bishop pair is valued at 6.25 rather than perhaps the naive 6 you would suggest).


1

There can't be a standard here so you can choose your scoring system in the way is makes most sense for your particular case. I'm not sure what its intent really is so it might be different from what I have in mind. We can all agree on what a 100% score would look like, but what does it really mean to have a 50% or a 75% score? If it's intended as a training ...


Only top voted, non community-wiki answers of a minimum length are eligible