{"id":24332672,"url":"https://github.com/silviatulli/rlhomework","last_synced_at":"2025-05-01T12:05:41.725Z","repository":{"id":84541945,"uuid":"162163090","full_name":"Silviatulli/RLhomework","owner":"Silviatulli","description":"multi-armed bandit, gambler problem, cliff problem and TD learning","archived":false,"fork":false,"pushed_at":"2021-06-02T16:14:42.000Z","size":18,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-05-01T12:05:24.085Z","etag":null,"topics":["cliff-problem","gambler-problem","multi-armed-bandit","sequential-decision-making-problems","td-learning"],"latest_commit_sha":null,"homepage":"","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/Silviatulli.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":"2018-12-17T16:57:30.000Z","updated_at":"2021-06-02T16:15:16.000Z","dependencies_parsed_at":"2023-03-05T14:30:51.187Z","dependency_job_id":null,"html_url":"https://github.com/Silviatulli/RLhomework","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/Silviatulli%2FRLhomework","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Silviatulli%2FRLhomework/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Silviatulli%2FRLhomework/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Silviatulli%2FRLhomework/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Silviatulli","download_url":"https://codeload.github.com/Silviatulli/RLhomework/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251871529,"owners_count":21657468,"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":["cliff-problem","gambler-problem","multi-armed-bandit","sequential-decision-making-problems","td-learning"],"created_at":"2025-01-18T02:38:52.974Z","updated_at":"2025-05-01T12:05:41.716Z","avatar_url":"https://github.com/Silviatulli.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Reinforcement Learning Homework\n\nThese exercises are part of the coursework for [Reinforcement Learning](https://fenix.tecnico.ulisboa.pt/disciplinas/TAIA/2019-2020/1-semestre/sumarios).\nYou will find the implementation of multi-armed bandit, gambler problem, cliff problem and TD learning.\n\n## Reference Book\n[Reinforcement Learning: An Introduction](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsilviatulli%2Frlhomework","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsilviatulli%2Frlhomework","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsilviatulli%2Frlhomework/lists"}