{"id":14958935,"url":"https://github.com/ukjin1192/tensorflow-minesweeper","last_synced_at":"2025-10-24T16:30:28.392Z","repository":{"id":94993106,"uuid":"83682203","full_name":"ukjin1192/TensorFlow-MineSweeper","owner":"ukjin1192","description":"Proof of concept for using TensorFlow to improve AI at this Minesweeper game","archived":false,"fork":false,"pushed_at":"2018-08-26T17:15:59.000Z","size":22,"stargazers_count":10,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-31T02:42:02.618Z","etag":null,"topics":["machine-learning","minesweeper-game","tensorflow","tensorflow-experiments"],"latest_commit_sha":null,"homepage":"https://minemine.io/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ukjin1192.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-03-02T13:43:15.000Z","updated_at":"2023-06-09T15:37:00.000Z","dependencies_parsed_at":"2023-06-07T14:45:52.952Z","dependency_job_id":null,"html_url":"https://github.com/ukjin1192/TensorFlow-MineSweeper","commit_stats":{"total_commits":18,"total_committers":1,"mean_commits":18.0,"dds":0.0,"last_synced_commit":"cb8f2c827b9d333e22d19fe3b3285b4c3b8f2ab8"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukjin1192%2FTensorFlow-MineSweeper","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukjin1192%2FTensorFlow-MineSweeper/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukjin1192%2FTensorFlow-MineSweeper/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukjin1192%2FTensorFlow-MineSweeper/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ukjin1192","download_url":"https://codeload.github.com/ukjin1192/TensorFlow-MineSweeper/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":237999465,"owners_count":19399886,"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":["machine-learning","minesweeper-game","tensorflow","tensorflow-experiments"],"created_at":"2024-09-24T13:18:33.470Z","updated_at":"2025-10-24T16:30:28.017Z","avatar_url":"https://github.com/ukjin1192.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Summary\n\n- Proof of concept for using TensorFlow to improve AI at \u003ca href=\"https://minemine.io\"\u003ethis Minesweeper game\u003c/a\u003e\n- Mission : Improve accuracy(=predictive power) when AI should sweep or flag random cell with given condition\n\n## Procedure\n\n- Create map randomly\n- Sweep empty block for the first time\n- Sweep or flag cells if AI could sweep or flag certain cell with given condition\n- Collect data when AI should sweep or flag random cell with given condition\n  - Target\n\t  - Unrevealed cell which has at least one revealed number cell(=not empty or mine) around\n\t- X data\n\t\t- Sum of probabilities\n\t\t- Number of revealed mines around\n\t\t- Number of revealed cells around\n\t\t- Number of unrevealed cell around\n\t- Y data\n\t\t- 0 or 1 (Mine exists or not)\n\t- Repeat above procedure many times to get enough data\n- Training sets\n\t- Method\n\t  - Supervised Learning\n\t\t- Logistic classification\n  - Optimization\n\t\t- Data initialization\n\t\t- Learning rate = 0.1\n- Test sets : Measure accuracy of model\n\n## Prerequisite\n\n- Python 3\n- Numpy\n- TensorFlow\n\n## Command\n\n~~~~\n$ python3 ai.py\n~~~~\n\n## Result\n\n- Collect data with 1000 games\n- 2000 training sets\n- (With test sets) Accuracy ~= 87(%)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukjin1192%2Ftensorflow-minesweeper","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fukjin1192%2Ftensorflow-minesweeper","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukjin1192%2Ftensorflow-minesweeper/lists"}