First published at 02:37 UTC on January 11th, 2022.
Four games against the chess engine Teki v2, with animation and music.
Teki uses an MCTS algorithm, but this technique seems badly implemented - it's laughable .. however, the non-MCTS version of Teki v2 has an ELO rating of 2340.
The first g…
MORE
Four games against the chess engine Teki v2, with animation and music.
Teki uses an MCTS algorithm, but this technique seems badly implemented - it's laughable .. however, the non-MCTS version of Teki v2 has an ELO rating of 2340.
The first game is against Weiawaga, another engine with rating around 2500, Teki plays the Black pieces. The other three games were played by me, the view is from my side.
In computer science, Monte Carlo tree search (MCTS) is a heuristic search algorithm for some kinds of decision processes, most notably those employed in software that plays board games. In that context MCTS is used to solve the game tree.
MCTS was combined with neural networks in 2016 for computer Go.[1] It has been used in other board games like chess and shogi,[2] games with incomplete information such as bridge[3] and poker,[4] as well as in turn-based-strategy video games (such as Total War: Rome II's implementation in the high level campaign AI). MCTS has also been used in self-driving cars, for example in Tesla's Autopilot software.
Source: https://en.wikipedia.org/wiki/Monte_Carlo_tree_search
replay the games :
https://lichess.org/xVqeFwA9
https://lichess.org/kcK0PRef/black
https://lichess.org/unmkeFpX
https://lichess.org/HizVkzc4/black
clips: some old train movie
music: "American Tango" by Weather Report
2022@ArtFlow - all rights respected
LESS