{"id":16536445,"url":"https://github.com/timbmg/easy21-rl","last_synced_at":"2025-10-08T19:34:22.856Z","repository":{"id":111550187,"uuid":"131485096","full_name":"timbmg/easy21-rl","owner":"timbmg","description":"Easy21 assignment from David Silver's RL Course at UCL","archived":false,"fork":false,"pushed_at":"2018-04-29T10:38:35.000Z","size":1649,"stargazers_count":12,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-08-02T09:12:50.356Z","etag":null,"topics":["function-approximation","monte-carlo","reinforcement-learning","reinforcement-learning-excercises","rl","sarsa","sarsa-lambda"],"latest_commit_sha":null,"homepage":null,"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/timbmg.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":"2018-04-29T10:27:17.000Z","updated_at":"2025-03-09T13:44:17.000Z","dependencies_parsed_at":"2023-03-08T03:30:31.465Z","dependency_job_id":null,"html_url":"https://github.com/timbmg/easy21-rl","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/timbmg/easy21-rl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timbmg%2Feasy21-rl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timbmg%2Feasy21-rl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timbmg%2Feasy21-rl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timbmg%2Feasy21-rl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/timbmg","download_url":"https://codeload.github.com/timbmg/easy21-rl/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timbmg%2Feasy21-rl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279000700,"owners_count":26082805,"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":"2025-10-08T02:00:06.501Z","response_time":56,"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":["function-approximation","monte-carlo","reinforcement-learning","reinforcement-learning-excercises","rl","sarsa","sarsa-lambda"],"created_at":"2024-10-11T18:31:26.965Z","updated_at":"2025-10-08T19:34:22.840Z","avatar_url":"https://github.com/timbmg.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Easy21 Implementation\n\nThis is an implementation of the Easy21 assignment of David Silver's Reinforcement Learning Course at UCL. The assignment can be found [here](http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/Easy21-Johannes.pdf).\n\n## Monte-Carlo Control\n\n`python3 mc.py`\n\n10 Million Episodes of the game have been evaluated, to obtain the following Value function:  \n\u003cimg src=\"https://github.com/timbmg/easy21/blob/master/figs/mc-value-function.png\" width=\"1000\"\u003e\n\n## TD Learning\n\n`python3 td.py`\n\nMean Squared Error of the state-action function of the Monte-Carlo experiment with different Lambdas. For each lambda, 10 000 Episodes have been evaluated.  \n\u003cimg src=\"https://github.com/timbmg/easy21/blob/master/figs/td-mse-lambda.png\" width=\"1000\"\u003e\n\nMean Squared Error evolution with different Lambdas.  \n\u003cimg src=\"https://github.com/timbmg/easy21/blob/master/figs/td-mse-episode-lambda.png\" width=\"1000\"\u003e\n\n## Linear Function Approximation\n\n`python3 lfa.py`\n\nThe lookup table of the previous experiment is replaced with a linear function approximation. The logic for the feature vector can be found in the assignment.  \n\n\u003cimg src=\"https://github.com/timbmg/easy21/blob/master/figs/lfa-mse-lambda.png\" width=\"1000\"\u003e\n  \n\u003cimg src=\"https://github.com/timbmg/easy21/blob/master/figs/lfa-mse-episode-lambda.png\" width=\"1000\"\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimbmg%2Feasy21-rl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftimbmg%2Feasy21-rl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimbmg%2Feasy21-rl/lists"}