{"id":22271238,"url":"https://github.com/gunh0/reinforcement-learning-cartpole-balancing","last_synced_at":"2026-03-08T05:32:20.219Z","repository":{"id":127668896,"uuid":"178683750","full_name":"gunh0/reinforcement-learning-cartpole-balancing","owner":"gunh0","description":"📢 2019 Microsoft Student Partners (MSP) Evangelism Seminar - 2019.03.31","archived":false,"fork":false,"pushed_at":"2024-09-03T05:18:21.000Z","size":6005,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-10-13T15:32:28.339Z","etag":null,"topics":["artificial-intelligence","cartpole","microsoft-student-partners","msp","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":false,"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/gunh0.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-03-31T12:16:30.000Z","updated_at":"2024-09-06T13:31:20.000Z","dependencies_parsed_at":null,"dependency_job_id":"838a6133-a464-4913-917c-8de1b2473d68","html_url":"https://github.com/gunh0/reinforcement-learning-cartpole-balancing","commit_stats":null,"previous_names":["gunh0/reinforcement-learning-cartpole-balancing"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gunh0/reinforcement-learning-cartpole-balancing","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gunh0%2Freinforcement-learning-cartpole-balancing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gunh0%2Freinforcement-learning-cartpole-balancing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gunh0%2Freinforcement-learning-cartpole-balancing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gunh0%2Freinforcement-learning-cartpole-balancing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gunh0","download_url":"https://codeload.github.com/gunh0/reinforcement-learning-cartpole-balancing/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gunh0%2Freinforcement-learning-cartpole-balancing/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30246727,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-08T00:58:18.660Z","status":"online","status_checked_at":"2026-03-08T02:00:06.215Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["artificial-intelligence","cartpole","microsoft-student-partners","msp","reinforcement-learning"],"created_at":"2024-12-03T12:11:14.714Z","updated_at":"2026-03-08T05:32:20.118Z","avatar_url":"https://github.com/gunh0.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"### 2019 Microsoft Student Partners (MSP) Evangelism Seminar\n\n**처음 시작하는 강화학습 with OpenAI Gym**\n\n**2019. 03. 31**\n\n![msp-logo.png](./docs/image/msp-logo.png)\n\n---\n\n**Cart Pole 균형 문제는 유전자 알고리즘, 인공신경망, 강화학습 등을 이용한 제어 전략 분야의 표준 문제이다.**\n\n![cartpole-task.gif](/docs/image/cartpole-task.gif)\n\n### Result (legacy)\n\n![result-old.png](./docs/image/result-old.png)\n\n\u003cbr/\u003e\n\n### Last Updated (2024. 01.)\n\n\u003e \u003chttps://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html\u003e\n\n- python 3.11.9\n\nThis tutorial shows how to use PyTorch to train a Deep Q Learning (DQN) agent on the CartPole-v1 task from Gymnasium.\n\n![output.png](./docs/image/output.png)\n\n**Diagram**\n\n![diagram.png](./docs/image/diagram.jpg)\n\nActions are chosen either randomly or based on a policy, getting the next step sample from the gym environment. We record the results in the replay memory and also run optimization step on every iteration. Optimization picks a random batch from the replay memory to do training of the new policy. The “older” target_net is also used in optimization to compute the expected Q values. A soft update of its weights are performed at every step.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgunh0%2Freinforcement-learning-cartpole-balancing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgunh0%2Freinforcement-learning-cartpole-balancing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgunh0%2Freinforcement-learning-cartpole-balancing/lists"}