{"id":23894351,"url":"https://github.com/princep/reinforcement-learning","last_synced_at":"2025-08-19T00:04:13.576Z","repository":{"id":88666345,"uuid":"114313380","full_name":"PrinceP/Reinforcement-Learning","owner":"PrinceP","description":"Implementation of RL problems","archived":false,"fork":false,"pushed_at":"2017-12-15T02:21:05.000Z","size":523,"stargazers_count":1,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-23T06:29:06.585Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/PrinceP.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":"2017-12-15T01:30:03.000Z","updated_at":"2020-12-17T20:31:44.000Z","dependencies_parsed_at":"2023-03-11T21:00:49.145Z","dependency_job_id":null,"html_url":"https://github.com/PrinceP/Reinforcement-Learning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/PrinceP/Reinforcement-Learning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrinceP%2FReinforcement-Learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrinceP%2FReinforcement-Learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrinceP%2FReinforcement-Learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrinceP%2FReinforcement-Learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PrinceP","download_url":"https://codeload.github.com/PrinceP/Reinforcement-Learning/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrinceP%2FReinforcement-Learning/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263640772,"owners_count":23493387,"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":[],"created_at":"2025-01-04T14:57:13.010Z","updated_at":"2025-07-05T00:36:40.929Z","avatar_url":"https://github.com/PrinceP.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Reinforcement-Learning\nImplementation of RL problems\n\nThe implementation of the Value Iteration and Q-Learning policy are done right now on the gridworld. \n\nThe sample problem is taken as below - \n\n![Problem](screenshot.png)\n![Problem](screenshot2.png)\n![Problem](screenshot3.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprincep%2Freinforcement-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprincep%2Freinforcement-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprincep%2Freinforcement-learning/lists"}