{"id":17223961,"url":"https://github.com/adeelh/rl_high_confidence_policy_improvement","last_synced_at":"2026-05-06T15:45:10.156Z","repository":{"id":81355790,"uuid":"226592382","full_name":"AdeelH/RL_high_confidence_policy_improvement","owner":"AdeelH","description":"High Confidence Policy Improvement for RL (class project for Reinforcement Learning, Fall 2019)","archived":false,"fork":false,"pushed_at":"2020-10-31T10:54:48.000Z","size":7318,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-30T14:34:41.464Z","etag":null,"topics":["machine-learning","optimization","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AdeelH.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":"2019-12-08T00:08:02.000Z","updated_at":"2020-10-31T11:01:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"987e2bba-f9dd-4314-bc5c-bcde1d665c58","html_url":"https://github.com/AdeelH/RL_high_confidence_policy_improvement","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/AdeelH%2FRL_high_confidence_policy_improvement","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdeelH%2FRL_high_confidence_policy_improvement/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdeelH%2FRL_high_confidence_policy_improvement/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdeelH%2FRL_high_confidence_policy_improvement/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AdeelH","download_url":"https://codeload.github.com/AdeelH/RL_high_confidence_policy_improvement/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245498046,"owners_count":20625106,"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":["machine-learning","optimization","reinforcement-learning"],"created_at":"2024-10-15T04:09:41.016Z","updated_at":"2026-05-06T15:45:10.110Z","avatar_url":"https://github.com/AdeelH.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# High Confidence Policy Improvement for RL\nGiven only the data from previous executions of a policy, but not the policy itself, generate a new policy that is probabilistically guaranteed to be better than the old policy.\n\nFor details: https://people.cs.umass.edu/~pthomas/papers/Thomas2015b.pdf\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadeelh%2Frl_high_confidence_policy_improvement","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadeelh%2Frl_high_confidence_policy_improvement","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadeelh%2Frl_high_confidence_policy_improvement/lists"}