{"id":18534264,"url":"https://github.com/keon/policy-gradient","last_synced_at":"2025-10-25T13:38:41.119Z","repository":{"id":82224396,"uuid":"82761215","full_name":"keon/policy-gradient","owner":"keon","description":"Minimal Monte Carlo Policy Gradient (REINFORCE) Algorithm Implementation in Keras","archived":false,"fork":false,"pushed_at":"2019-12-26T09:29:43.000Z","size":3711,"stargazers_count":160,"open_issues_count":3,"forks_count":43,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-04-10T09:50:41.858Z","etag":null,"topics":["deep-reinforcement-learning","keras","policy-gradient","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","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/keon.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":"2017-02-22T04:38:31.000Z","updated_at":"2025-04-08T16:20:16.000Z","dependencies_parsed_at":"2023-04-05T10:46:22.281Z","dependency_job_id":null,"html_url":"https://github.com/keon/policy-gradient","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/keon/policy-gradient","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keon%2Fpolicy-gradient","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keon%2Fpolicy-gradient/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keon%2Fpolicy-gradient/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keon%2Fpolicy-gradient/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/keon","download_url":"https://codeload.github.com/keon/policy-gradient/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keon%2Fpolicy-gradient/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":280965081,"owners_count":26421547,"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","status":"online","status_checked_at":"2025-10-25T02:00:06.499Z","response_time":81,"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":["deep-reinforcement-learning","keras","policy-gradient","reinforcement-learning"],"created_at":"2024-11-06T19:15:09.814Z","updated_at":"2025-10-25T13:38:41.114Z","avatar_url":"https://github.com/keon.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Policy Gradient\n\nMinimal implementation of Stochastic Policy Gradient Algorithm in Keras\n\n## Pong Agent\n\n![pg](./assets/pg.gif)\n\n\nThis PG agent seems to get more frequent wins after about 8000 episodes. Below is the score graph.\n\n\n![score](./assets/score.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeon%2Fpolicy-gradient","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkeon%2Fpolicy-gradient","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeon%2Fpolicy-gradient/lists"}