{"id":25573108,"url":"https://github.com/jeffasante/grpo-maze-solver","last_synced_at":"2026-03-22T21:30:18.765Z","repository":{"id":276495869,"uuid":"929412759","full_name":"jeffasante/grpo-maze-solver","owner":"jeffasante","description":"A reinforcement learning agent that learns to solve mazes using Group Relative Policy Optimization (GRPO).","archived":false,"fork":false,"pushed_at":"2025-02-08T16:29:41.000Z","size":3,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-08T16:33:31.784Z","etag":null,"topics":["deep-seek-r1-grpo","group-relative-policy-optimization","reinforcement-learning-agent"],"latest_commit_sha":null,"homepage":"","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/jeffasante.png","metadata":{},"created_at":"2025-02-08T13:48:59.000Z","updated_at":"2025-02-08T16:29:44.000Z","dependencies_parsed_at":null,"dependency_job_id":"743152c0-7c45-4025-b80f-b825c709c68d","html_url":"https://github.com/jeffasante/grpo-maze-solver","commit_stats":null,"previous_names":["jeffasante/grpo-maze-solver"],"tags_count":null,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeffasante%2Fgrpo-maze-solver","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeffasante%2Fgrpo-maze-solver/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeffasante%2Fgrpo-maze-solver/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jeffasante%2Fgrpo-maze-solver/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jeffasante","download_url":"https://codeload.github.com/jeffasante/grpo-maze-solver/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239938046,"owners_count":19721557,"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":["deep-seek-r1-grpo","group-relative-policy-optimization","reinforcement-learning-agent"],"created_at":"2025-02-21T01:20:04.101Z","updated_at":"2026-03-22T21:30:18.735Z","avatar_url":"https://github.com/jeffasante.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjeffasante%2Fgrpo-maze-solver","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjeffasante%2Fgrpo-maze-solver","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjeffasante%2Fgrpo-maze-solver/lists"}