{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/monte-carlo-tree-search-for-asymmetric-trees","title":"Monte Carlo Tree Search for Asymmetric Trees","arxiv_id":"1805.09218","date":"2018-05-23","proceeding":null,"authors":["Thomas M. Moerland","Joost Broekens","Aske Plaat","Catholijn M. Jonker"],"abstract":"We present an extension of Monte Carlo Tree Search (MCTS) that strongly\nincreases its efficiency for trees with asymmetry and/or loops. Asymmetric\ntermination of search trees introduces a type of uncertainty for which the\nstandard upper confidence bound (UCB) formula does not account. Our first\nalgorithm (MCTS-T), which assumes a non-stochastic environment, backs-up tree\nstructure uncertainty and leverages it for exploration in a modified UCB\nformula. Results show vastly improved efficiency in a well-known asymmetric\ndomain in which MCTS performs arbitrarily bad. Next, we connect the ideas about\nasymmetric termination to the presence of loops in the tree, where the same\nstate appears multiple times in a single trace. An extension to our algorithm\n(MCTS-T+), which in addition to non-stochasticity assumes full state\nobservability, further increases search efficiency for domains with loops as\nwell. Benchmark testing on a set of OpenAI Gym and Atari 2600 games indicates\nthat our algorithms always perform better than or at least equivalent to\nstandard MCTS, and could be first-choice tree search algorithms for\nnon-stochastic, fully-observable environments.","url_abs":"http://arxiv.org/abs/1805.09218v1","url_pdf":"http://arxiv.org/pdf/1805.09218v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"monte-carlo-tree-search-for-asymmetric-trees","repo_url":"https://github.com/tmoer/mcts-t","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"monte-carlo-tree-search-for-asymmetric-trees","repo_url":"https://github.com/jeapostrophe/monaco","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}