{"id":20315568,"url":"https://github.com/burz/gobot","last_synced_at":"2025-04-11T17:26:03.531Z","repository":{"id":24362614,"uuid":"27761475","full_name":"burz/gobot","owner":"burz","description":"Learning to score the game of Go","archived":false,"fork":false,"pushed_at":"2015-09-05T00:35:25.000Z","size":10264,"stargazers_count":3,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-25T13:21:11.398Z","etag":null,"topics":["board","machine-learning","scoring","sgf"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/burz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2014-12-09T10:29:56.000Z","updated_at":"2021-08-19T02:51:24.000Z","dependencies_parsed_at":"2022-08-22T16:31:04.847Z","dependency_job_id":null,"html_url":"https://github.com/burz/gobot","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/burz%2Fgobot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/burz%2Fgobot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/burz%2Fgobot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/burz%2Fgobot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/burz","download_url":"https://codeload.github.com/burz/gobot/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248448713,"owners_count":21105348,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["board","machine-learning","scoring","sgf"],"created_at":"2024-11-14T18:19:52.818Z","updated_at":"2025-04-11T17:26:03.489Z","avatar_url":"https://github.com/burz.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"gobot\n=====\n\nA machine learning algorithm for learning to score the final board in the game of Go\n\n### Background\n\nI wrote this for my machine learning final project during my senior of college.\n[Here's the final paper I wrote.](https://github.com/burz/burz.github.io/blob/master/finalReport.pdf)\nThis paper reflects the state of gobot at the [finalProject](https://github.com/burz/gobot/tree/finalProject)\nbranch. It reads in `.sgf` files, and due to the linear nature of the `.sgf` file format, it must play through an\nentire game to reach the final board position. Note that a stone can be placed where another had been placed before being\ncaptured and removed from the board.\n\nAfter I had submitted the project, I set out to up the learning algorithm by saving the boards to files rather than\nrunning through the games each time. Furthermore, I reverted back to the\n[original paper's algorithm](http://erikvanderwerf.tengen.nl/pubdown/learning_to_score_extended.pdf)\nthat I had based my project upon, and implemented my proposed bootstrapping method to generate good labels for\nthousands of games (I was using datasets of 20,000+ games for my finalProject version of the algorithm).\n\n### Current results\n\nAt the time, I was getting bad results, while using the bootstrap I had found that for many of the games in my dataset,\nthe reported score in the `.sgf` was incorrect. Usually it was off by 1 or 2 points from what the actual board should have\nbeen scored in that state.\n\nAfter further reasearch I discovered that most of these records assumed end game moves of varying complexity\nwould be played out, but the `.sgf`'s did not reflect these intuitions.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fburz%2Fgobot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fburz%2Fgobot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fburz%2Fgobot/lists"}