{"id":18305773,"url":"https://github.com/yaricom/rl-playground","last_synced_at":"2026-04-30T16:33:26.294Z","repository":{"id":94042772,"uuid":"58407878","full_name":"yaricom/RL-playground","owner":"yaricom","description":"The RL playground. Experiments with RL algorithms","archived":false,"fork":false,"pushed_at":"2016-05-10T14:16:09.000Z","size":8,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-07-03T12:06:06.011Z","etag":null,"topics":["learning-agents","openai","reinforcement-learning","rl-playground"],"latest_commit_sha":null,"homepage":null,"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/yaricom.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":"2016-05-09T21:00:38.000Z","updated_at":"2022-07-29T04:18:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"bf331085-ea1e-453d-b8af-5b94e1d19bcd","html_url":"https://github.com/yaricom/RL-playground","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/yaricom/RL-playground","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yaricom%2FRL-playground","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yaricom%2FRL-playground/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yaricom%2FRL-playground/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yaricom%2FRL-playground/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yaricom","download_url":"https://codeload.github.com/yaricom/RL-playground/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yaricom%2FRL-playground/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32470879,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"ssl_error","status_checked_at":"2026-04-30T13:12:06.837Z","response_time":57,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["learning-agents","openai","reinforcement-learning","rl-playground"],"created_at":"2024-11-05T15:35:42.112Z","updated_at":"2026-04-30T16:33:26.277Z","avatar_url":"https://github.com/yaricom.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RL-playground\nIn this repository some of my experiments with Reinforcement Learning algorithms based on [OpenAi Gym ToolKit](https://gym.openai.com)\n\n## Overview\nPackages:\n- [openai/envs](https://github.com/yaricom/RL-playground/tree/master/openai/envs) the OpenAi Gym compatible environments for evaluation\n- [openai/agents](https://github.com/yaricom/RL-playground/tree/master/openai/agents) the learning agents\n\nEnvironments:\n- [NArmedBanditEnv](https://github.com/yaricom/RL-playground/blob/master/openai/envs/classic/narmedbandit.py) - N-armed bandit (stationary, nonstationary)\n\nLearning agents:\n- [SampleAverageActionValueAgent](https://github.com/yaricom/RL-playground/blob/master/openai/agents/sampleaverage.py) - the learning agent based on sample-average action-value selection algorithm for both stationary and nonstationary environments\n\n## Usage\n```Python\nimport gym\n\nfrom openai.agents.sampleaverage import SampleAverageActionValueAgent\n\ndef main():\n    # load environment\n    env = gym.make('10ArmedBanditStationary-v0')\n\n    # setup\n    agent = SampleAverageActionValueAgent(num_actions = 10)\n    episode_count = 1\n    max_steps = 100\n    reward = 0\n    done = False\n\n    for i in xrange(episode_count):\n        ob = env.reset()\n\n        for j in xrange(max_steps):\n            action = agent.evaluate(reward, done)\n            ob, reward, done, _ = env.step(action)\n            if done:\n                break\n\n\nif __name__ == '__main__':\n    main()\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyaricom%2Frl-playground","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyaricom%2Frl-playground","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyaricom%2Frl-playground/lists"}