Monte Carlo tree search

<p>In <a href="/facts/Computer_science/lN3pEyPz">computer science</a>, Monte Carlo tree search (MCTS) is a <a href="/facts/Heuristic_(computer_science)/PM2qkoa2">heuristic</a> <a href="/facts/Search_algorithm/eJuw0nyz">search algorithm</a> for some kinds of <a href="/facts/Decision_process/NbJYprSw">decision processes</a>, most notably those employed in <a href="/facts/Software/RP79lVSW">software</a> that plays <a href="/facts/Board_game/ctkuzWJU">board games</a>. In that context MCTS is used to solve the <a href="/facts/Game_tree/qQX93S4l">game tree</a>.
</p><p>MCTS was combined with neural networks in 2016 and has been used in multiple board games like <a href="/facts/Chess/47ykvkHF">Chess</a>, <a href="/facts/Shogi/z12HJ3vB">Shogi</a>, <a href="/facts/Checkers/zrzKMsyu">Checkers</a>, <a href="/facts/Backgammon/53mgqvtv">Backgammon</a>, <a href="/facts/Contract_Bridge/ohDtVpd9">Contract Bridge</a>, <a href="/facts/Go_(game)/1fKhemww">Go</a>, <a href="/facts/Scrabble/BxpF5qNv">Scrabble</a>, and <a href="/facts/Clobber/tPxuPUQe">Clobber</a> as well as in turn-based-strategy video games (such as <a href="/facts/Total_War%3a_Rome_II/eQbCdCjU">Total War: Rome II</a>'s implementation in the high level campaign AI) and applications outside of games.
</p>

Monte Carlo tree search open-in-new

Monte Carlo tree search