{"id":20782461,"url":"https://github.com/awjuliani/meta-rl","last_synced_at":"2025-04-07T09:20:35.706Z","repository":{"id":38806386,"uuid":"80312817","full_name":"awjuliani/Meta-RL","owner":"awjuliani","description":"Implementation of Meta-RL A3C algorithm","archived":false,"fork":false,"pushed_at":"2017-02-22T17:12:45.000Z","size":834,"stargazers_count":402,"open_issues_count":4,"forks_count":109,"subscribers_count":25,"default_branch":"master","last_synced_at":"2025-03-31T08:08:54.661Z","etag":null,"topics":["reinforcement-learning","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/awjuliani.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}},"created_at":"2017-01-28T21:43:45.000Z","updated_at":"2025-03-28T05:15:07.000Z","dependencies_parsed_at":"2022-08-09T06:02:00.698Z","dependency_job_id":null,"html_url":"https://github.com/awjuliani/Meta-RL","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/awjuliani%2FMeta-RL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/awjuliani%2FMeta-RL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/awjuliani%2FMeta-RL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/awjuliani%2FMeta-RL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/awjuliani","download_url":"https://codeload.github.com/awjuliani/Meta-RL/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247622983,"owners_count":20968575,"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":["reinforcement-learning","tensorflow"],"created_at":"2024-11-17T14:11:20.737Z","updated_at":"2025-04-07T09:20:35.661Z","avatar_url":"https://github.com/awjuliani.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Meta-RL\nTensorflow implementation of Meta-RL A3C algorithm taken from [Learning to Reinforcement Learn](https://arxiv.org/abs/1611.05763). \nFor more information, as well as explainations of each of the experiments, see my corresponding [Medium post](https://medium.com/p/b15b592a2ddf). A3C is built from previous implementation available [here](https://github.com/awjuliani/DeepRL-Agents).\n\nContains iPython notebooks for:\n\n* **A3C-Meta-Bandit** - Set of bandit tasks described in paper. Including: Independent, Dependent, and Restless bandits.\n* **A3C-Meta-Context** - Rainbow bandit task using randomized colors to indicate reward-giving arm in each episode. \n* **A3C-Meta-Grid** - Rainbow Gridworld task; a variation of gridworld in which goal colors are randomzied each episode and must be learned \"on the fly.\"\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fawjuliani%2Fmeta-rl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fawjuliani%2Fmeta-rl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fawjuliani%2Fmeta-rl/lists"}