{"id":17595152,"url":"https://github.com/takuseno/rsvg","last_synced_at":"2025-04-12T07:12:40.330Z","repository":{"id":80512644,"uuid":"113405330","full_name":"takuseno/rsvg","owner":"takuseno","description":"Recurrent Stochastic Value Gradient implementation with TensorFlow","archived":false,"fork":false,"pushed_at":"2018-04-22T08:20:48.000Z","size":12,"stargazers_count":7,"open_issues_count":1,"forks_count":3,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-12T07:12:35.867Z","etag":null,"topics":["reinforcement-learning","tensorflow"],"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/takuseno.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}},"created_at":"2017-12-07T05:06:19.000Z","updated_at":"2023-09-27T16:07:17.000Z","dependencies_parsed_at":"2023-04-01T15:34:36.567Z","dependency_job_id":null,"html_url":"https://github.com/takuseno/rsvg","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/takuseno%2Frsvg","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/takuseno%2Frsvg/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/takuseno%2Frsvg/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/takuseno%2Frsvg/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/takuseno","download_url":"https://codeload.github.com/takuseno/rsvg/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248530571,"owners_count":21119600,"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":"2024-10-22T07:38:00.314Z","updated_at":"2025-04-12T07:12:40.295Z","avatar_url":"https://github.com/takuseno.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## RSVG\nRecurrent Stochastic Value Gradient implementation with Tensorflow.\n\nhttps://arxiv.org/pdf/1512.04455.pdf\n\n## requirements\n- Python3\n\n## dependencies\n- tensorflow\n- gym[atari]\n- opencv-python\n- git+https://github.com/imai-laboratory/lightsaber\n\n## usage\n### training\n```\n$ python train.py [--render] --final-steps 10000000\n```\n\n### playing\n```\n$ python train.py [--render] --load {path of models} --demo\n```\n\n### implementation\nThis is inspired by following projects.\n\n- [DQN](https://github.com/imai-laboratory/dqn)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftakuseno%2Frsvg","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftakuseno%2Frsvg","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftakuseno%2Frsvg/lists"}