{"id":20290185,"url":"https://github.com/daniel-m-campos/deep_rl","last_synced_at":"2026-04-19T10:31:52.949Z","repository":{"id":214419317,"uuid":"394407855","full_name":"daniel-m-campos/deep_rl","owner":"daniel-m-campos","description":"Deep Reinforcement Learning examples from Udacity's Deep RL Nano Degree","archived":false,"fork":false,"pushed_at":"2021-10-06T00:09:27.000Z","size":2669,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-08-02T21:48:30.650Z","etag":null,"topics":["deep-reinforcement-learning","udacity","unity"],"latest_commit_sha":null,"homepage":"","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/daniel-m-campos.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}},"created_at":"2021-08-09T19:02:38.000Z","updated_at":"2021-10-06T00:09:30.000Z","dependencies_parsed_at":"2023-12-28T04:35:32.706Z","dependency_job_id":null,"html_url":"https://github.com/daniel-m-campos/deep_rl","commit_stats":null,"previous_names":["daniel-m-campos/deep_rl"],"tags_count":1,"template":false,"template_full_name":"daniel-m-campos/python_template","purl":"pkg:github/daniel-m-campos/deep_rl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daniel-m-campos%2Fdeep_rl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daniel-m-campos%2Fdeep_rl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daniel-m-campos%2Fdeep_rl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daniel-m-campos%2Fdeep_rl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/daniel-m-campos","download_url":"https://codeload.github.com/daniel-m-campos/deep_rl/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daniel-m-campos%2Fdeep_rl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32004019,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T20:23:30.271Z","status":"online","status_checked_at":"2026-04-19T02:00:07.110Z","response_time":55,"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":["deep-reinforcement-learning","udacity","unity"],"created_at":"2024-11-14T15:06:33.452Z","updated_at":"2026-04-19T10:31:52.929Z","avatar_url":"https://github.com/daniel-m-campos.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep RL [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n\n## Environments\n\n1. [Navigation](docs/Navigation.md)\n2. [Continuous Control](docs/ContinuousControl.md)\n3. [Tennis](docs/Tennis.md)\n\n## Installation\n\nTo easily install the package, clone the repository and use a `virtualenv` to pip install the package in developer mode.\n\n```bash\ngit clone https://github.com/daniel-m-campos/deep_rl.git\ncd deep_rl\npython -m venv venv # make sure Python 3.6\n. venv/bin/activate\npip install -e .\n```\n\n### Requirements\n\nSee `requirements.txt` and `text-requiremnets.txt`. These are installed during the `pip install` step.\n\n### Binary dependencies\n\nThe package depends on the Udacity's Unity Environments. See [Environments](#Environments) for the binary download\nlinks.\n\nThe default binary paths are set in the `Environment` implementations and are of the\nform `/usr/local/sbin/\u003cENVIRONMENT\u003e.x86_64`. See the `Navigation` class in `environment.py` for an example. You can\neither symlink the downloaded binaries to the default directories or pass the `binary_path` when running the package.\n\n## Usage\n\nThe package provides a [Fire](https://github.com/google/python-fire) CLI for training and playing the agent. To see the\nbasic commands:\n\n```bash\ncd deep_rl\n. venv/bin/activate\npython -m deep_rl \u003ccommand\u003e --help\n```\n\nWhere `\u003ccommand\u003e` is either `train` or `play`. See `deep_rl/__main__.py` as well as the `__init__` method of `Agent`\nimplementations in `deep_rl/agent.py`\n\n### Train\n\nTo train an agent in the Navigation/Banana Unity environment with default parameters, run:\n\n```bash\ncd deep_rl\n. venv/bin/activate\npython -m deep_rl train navigation\n```\n\nTo train with custom parameters, run for example:\n\n```bash\npython -m deep_rl train navigation \\\n  --n_episodes=100 \\\n  --save_path=None \\\n  --image_path=None \\\n  --learning_rate=5e-3\n```\n\n### Play\n\n#### Navigation\n\nTo play an agent in the Navigation/Banana environment with default parameters, run:\n\n```bash\ncd deep_rl\n. venv/bin/activate\npython -m deep_rl play navigation\n```\n\nTo play with alternative network, run\n\n```bash\npython -m deep_rl play navigation --load_path=\"path_to_your/network.pth\"\n```\n\n#### Continuous Control\n\nTo play an agent in the Continuous Control/Reacher environment with default parameters, run:\n\n```bash\ncd deep_rl\n. venv/bin/activate\npython -m deep_rl play continuous_control\n```\n\n#### Tennis\n\nTo play an agent in the Tennis environment with default parameters, run:\n\n```bash\ncd deep_rl\n. venv/bin/activate\npython -m deep_rl play tennis\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdaniel-m-campos%2Fdeep_rl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdaniel-m-campos%2Fdeep_rl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdaniel-m-campos%2Fdeep_rl/lists"}