{"id":18673831,"url":"https://github.com/qasimwani/policy-value-methods","last_synced_at":"2025-04-12T01:32:00.601Z","repository":{"id":101529709,"uuid":"282768935","full_name":"QasimWani/policy-value-methods","owner":"QasimWani","description":"Deep Reinforcement Learning algorithms for Policy Value methods written from scratch.","archived":false,"fork":false,"pushed_at":"2020-08-27T08:46:03.000Z","size":407662,"stargazers_count":23,"open_issues_count":1,"forks_count":5,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-09T05:51:53.826Z","etag":null,"topics":["a3c-lstm","actor-critic","algorithms","augmented-random-search","ddpg","deep-neural-networks","deep-reinforcement-learning","evolutionary-algorithms","openai-gym","policy-gradient","proximal-policy-optimization","reinforce","td3"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/QasimWani.png","metadata":{},"created_at":"2020-07-27T01:51:27.000Z","updated_at":"2025-03-03T05:46:34.000Z","dependencies_parsed_at":null,"dependency_job_id":"37c63e17-027a-4c9a-bd6e-c837ca3bd218","html_url":"https://github.com/QasimWani/policy-value-methods","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/QasimWani%2Fpolicy-value-methods","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QasimWani%2Fpolicy-value-methods/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QasimWani%2Fpolicy-value-methods/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QasimWani%2Fpolicy-value-methods/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/QasimWani","download_url":"https://codeload.github.com/QasimWani/policy-value-methods/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248504292,"owners_count":21115142,"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":["a3c-lstm","actor-critic","algorithms","augmented-random-search","ddpg","deep-neural-networks","deep-reinforcement-learning","evolutionary-algorithms","openai-gym","policy-gradient","proximal-policy-optimization","reinforce","td3"],"created_at":"2024-11-07T09:16:40.825Z","updated_at":"2025-04-12T01:32:00.595Z","avatar_url":"https://github.com/QasimWani.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqasimwani%2Fpolicy-value-methods","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqasimwani%2Fpolicy-value-methods","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqasimwani%2Fpolicy-value-methods/lists"}