{"id":13689449,"url":"https://github.com/kashif/firedup","last_synced_at":"2025-04-10T22:38:46.296Z","repository":{"id":66482594,"uuid":"159047791","full_name":"kashif/firedup","owner":"kashif","description":"Clone of OpenAI's Spinning Up in PyTorch","archived":false,"fork":false,"pushed_at":"2022-04-19T10:56:23.000Z","size":155,"stargazers_count":146,"open_issues_count":2,"forks_count":25,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-11-12T13:39:07.966Z","etag":null,"topics":["deep-learning","pytorch","reinforcement-learning","spinningup"],"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/kashif.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-11-25T15:46:43.000Z","updated_at":"2024-09-12T09:43:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"bf06acc7-011e-4910-b76d-f6726e89cd20","html_url":"https://github.com/kashif/firedup","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/kashif%2Ffiredup","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kashif%2Ffiredup/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kashif%2Ffiredup/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kashif%2Ffiredup/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kashif","download_url":"https://codeload.github.com/kashif/firedup/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226188269,"owners_count":17587475,"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-learning","pytorch","reinforcement-learning","spinningup"],"created_at":"2024-08-02T15:01:48.352Z","updated_at":"2024-11-24T16:26:21.606Z","avatar_url":"https://github.com/kashif.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Welcome to Fired Up in Deep RL!\n\n\nThis is a clone of OpenAI's [Spinning Up](https://github.com/openai/spinningup) in PyTorch. Spinning Up is an awesome educational resource produced by Josh Achiam, a  research scientist at [OpenAI](https://openai.com/), that makes it easier to learn about deep reinforcement learning (deep RL).\n\n## Installation\n\nFired Up requires Python3, PyTorch, OpenAI Gym, and OpenMPI.\n\nFired Up is currently only supported on Linux and OSX. It may be possible to install on Windows, though I  haven't tested this OS.\n\n### Installing Python\n\nWe recommend installing Python through [Anaconda](https://www.anaconda.com/distribution/#download-section). Anaconda is a Python distribution that includes many useful packages especially for scientific computing, as well as an environment manager called `conda` that makes package management simple.\n\nDownload and install Anaconda 2018.x (at time of writing, 2018.12) Python 3.7. Then create a `conda` environment for organizing packages used in Fired Up:\n\n```\nconda create -n firedup python=3.7\n```\n\nTo use Python from the environment you just created, activate the environment with:\n\n```\nsource activate firedup\n```\n\nYou can alternatively use [virtualenv](https://virtualenv.pypa.io/en/latest/) with the Python3 version you have. Just install it via `pip3` and then:\n\n```\nvirtualenv firedup\n```\n\nTo activate this virtual environment you need to:\n\n```\nsource /path/to/firedup/bin/activate\n```\n\n### Installing OpenMPI\n\n#### Ubuntu\n\n```\nsudo apt update \u0026\u0026 sudo apt install libopenmpi-dev\n```\n\n#### Mac OS X\n\nInstallation of system packages on Mac requires [Homebrew](https://brew.sh). With Homebrew installed, run the following:\n\n```\nbrew install openmpi\n```\n\n### Installing Fired Up\n\n```\ngit clone https://github.com/kashif/firedup.git\ncd firedup\npip install -e .\n```\n\nFired Up defaults to installing everything in Gym **except** the MuJoCo environments.\n\n### Check Your Install\n\nTo see if you've successfully installed Fired Up, try running PPO in the `LunarLander-v2` environment with:\n\n```\npython -m fireup.run ppo --hid \"[32,32]\" --env LunarLander-v2 --exp_name installtest --gamma 0.999\n```\n\nAfter it finishes training, watch a video of the trained policy with:\n\n```\npython -m fireup.run test_policy data/installtest/installtest_s0\n```\n\nAnd plot the results with:\n\n```\npython -m fireup.run plot data/installtest/installtest_s0\n```\n\n## Algorithms\n\nThe following algorithms are implemented in the Fired Up package:\n\n* Vanilla Policy Gradient (VPG)\n* Trust Region Policy Optimization (TRPO)\n* Proximal Policy Optimization (PPO)\n* Deep Q-Network (DQN)\n* Deep Deterministic Policy Gradient (DDPG)\n* Twin Delayed DDPG (TD3)\n* Soft Actor-Critic (SAC)\n\nThey are all implemented with MLP (non-recurrent) actor-critics, making them suitable for fully-observed, non-image-based RL environments, e.g. the Gym Mujoco environments.\n\n## Citation\n\nIf you use Fired Up in your research please  use the following BibTeX entry:\n\n```BibTeX\n@misc{rasulfiredup,\n  author =       {Kashif Rasul and Joshua Achiam},\n  title =        {Fired Up},\n  howpublished = {\\url{https://github.com/kashif/firedup/}},\n  year =         {2019}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkashif%2Ffiredup","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkashif%2Ffiredup","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkashif%2Ffiredup/lists"}