{"id":18673749,"url":"https://github.com/carpedm20/naf-tensorflow","last_synced_at":"2025-08-21T05:32:41.037Z","repository":{"id":66039962,"uuid":"62736351","full_name":"carpedm20/NAF-tensorflow","owner":"carpedm20","description":"\"Continuous Deep Q-Learning with Model-based Acceleration\" in TensorFlow","archived":false,"fork":false,"pushed_at":"2018-07-20T23:40:54.000Z","size":504,"stargazers_count":193,"open_issues_count":7,"forks_count":59,"subscribers_count":17,"default_branch":"master","last_synced_at":"2024-12-09T07:28:46.684Z","etag":null,"topics":["continuous-rl","deep-learning","deep-reinforcement-learning","gym","reinforcement-learning","tensorflow"],"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/carpedm20.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}},"created_at":"2016-07-06T16:25:42.000Z","updated_at":"2024-01-04T16:05:59.000Z","dependencies_parsed_at":"2023-04-05T03:47:47.524Z","dependency_job_id":null,"html_url":"https://github.com/carpedm20/NAF-tensorflow","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/carpedm20%2FNAF-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/carpedm20%2FNAF-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/carpedm20%2FNAF-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/carpedm20%2FNAF-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/carpedm20","download_url":"https://codeload.github.com/carpedm20/NAF-tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":230494917,"owners_count":18235046,"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":["continuous-rl","deep-learning","deep-reinforcement-learning","gym","reinforcement-learning","tensorflow"],"created_at":"2024-11-07T09:16:28.862Z","updated_at":"2024-12-19T20:07:28.832Z","avatar_url":"https://github.com/carpedm20.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Normalized Advantage Functions (NAF) in TensorFlow\n\nTensorFlow implementation of [Continuous Deep q-Learning with Model-based Acceleration](http://arxiv.org/abs/1603.00748).\n\n![algorithm](https://github.com/carpedm20/naf-tensorflow/blob/master/assets/algorithm.png)\n\n\n## Requirements\n\n- Python 2.7\n- [gym](https://github.com/openai/gym)\n- [TensorFlow](https://www.tensorflow.org/) 0.9+\n\n\n## Usage\n\nFirst, install prerequisites with:\n\n    $ pip install tqdm gym[all]\n\nTo train a model for an environment with a continuous action space:\n\n    $ python main.py --env_name=Pendulum-v0 --is_train=True\n    $ python main.py --env_name=Pendulum-v0 --is_train=True --display=True\n\nTo test and record the screens with gym:\n\n    $ python main.py --env_name=Pendulum-v0 --is_train=False\n    $ python main.py --env_name=Pendulum-v0 --is_train=False --display=True\n\n\n## Results\n\nTraining details of `Pendulum-v0` with different hyperparameters.\n\n    $ python main.py --env_name=Pendulum-v0 # dark green\n    $ python main.py --env_name=Pendulum-v0 --action_fn=tanh # light green\n    $ python main.py --env_name=Pendulum-v0 --use_batch_norm=True # yellow\n    $ python main.py --env_name=Pendulum-v0 --use_seperate_networks=True # green\n\n![Pendulum-v0_2016-07-15](https://github.com/carpedm20/naf-tensorflow/blob/master/assets/Pendulum-v0_2016-07-15.png)\n\n\n## References\n\n- [rllab](https://github.com/rllab/rllab.git)\n- [keras implementation](https://gym.openai.com/evaluations/eval_CzoNQdPSAm0J3ikTBSTCg)\n\n\n## Author\n\nTaehoon Kim / [@carpedm20](http://carpedm20.github.io/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcarpedm20%2Fnaf-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcarpedm20%2Fnaf-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcarpedm20%2Fnaf-tensorflow/lists"}