{"id":27384850,"url":"https://github.com/tgangwani/selfimitationdiverse","last_synced_at":"2025-10-04T05:49:51.180Z","repository":{"id":94267991,"uuid":"184829120","full_name":"tgangwani/SelfImitationDiverse","owner":"tgangwani","description":"Tensorflow code for \"Learning Self-Imitating Diverse Policies\" (ICLR 2019)","archived":false,"fork":false,"pushed_at":"2020-11-26T20:50:07.000Z","size":28,"stargazers_count":19,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-13T16:48:02.359Z","etag":null,"topics":["deep-learning","imitation-learning","reinforcement-learning","tensorflow"],"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/tgangwani.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,"zenodo":null}},"created_at":"2019-05-03T22:49:57.000Z","updated_at":"2022-09-08T14:10:54.000Z","dependencies_parsed_at":"2023-07-27T19:16:46.278Z","dependency_job_id":null,"html_url":"https://github.com/tgangwani/SelfImitationDiverse","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/tgangwani/SelfImitationDiverse","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgangwani%2FSelfImitationDiverse","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgangwani%2FSelfImitationDiverse/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgangwani%2FSelfImitationDiverse/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgangwani%2FSelfImitationDiverse/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tgangwani","download_url":"https://codeload.github.com/tgangwani/SelfImitationDiverse/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tgangwani%2FSelfImitationDiverse/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278271876,"owners_count":25959523,"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":"2025-10-04T02:00:05.491Z","response_time":63,"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-learning","imitation-learning","reinforcement-learning","tensorflow"],"created_at":"2025-04-13T16:36:35.295Z","updated_at":"2025-10-04T05:49:51.175Z","avatar_url":"https://github.com/tgangwani.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"This repo contains code for our paper [Learning Self-Imitating Diverse Policies](https://arxiv.org/abs/1805.10309) published at ICLR 2019. \n\nThe code was tested with the following packages:\n\n* python 3.5.2\n* tensorflow 1.4.0\n* gym  0.9.2\n\n## Running command\nTo train a self-imitation agent in an episodic reward environment, use:\n\n```\npython main.py --env_id HalfCheetah-v1 --seed=$(echo $RANDOM) --mu=0.8 --episodic\n```\n\nThe parameter 'mu' is as defined in the paper (Equation 5.)\n\n## SVPG for diverse multi-agent training\nThis functionality is provided as part of a separate codebase. Please use the code [here](https://github.com/tgangwani/QDAgents) with the following configuration in the file __default_config.yaml__: divergence: js, dre_type: nce \n\n## Credits\nThe code is built on, and uses many utils from [OpenAI baselines](https://github.com/openai/baselines)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftgangwani%2Fselfimitationdiverse","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftgangwani%2Fselfimitationdiverse","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftgangwani%2Fselfimitationdiverse/lists"}