{"id":16360056,"url":"https://github.com/frgfm/drlnd-p2-continuous-control","last_synced_at":"2026-05-08T01:40:23.668Z","repository":{"id":110056010,"uuid":"221333652","full_name":"frgfm/drlnd-p2-continuous-control","owner":"frgfm","description":"Continuous control project of Udacity Deep Reinforcement Learning Nanodegree","archived":false,"fork":false,"pushed_at":"2019-11-13T11:30:45.000Z","size":242,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-12-29T17:41:35.071Z","etag":null,"topics":["actor-critic","ddpg-algorithm","deep-reinforcement-learning","experience-replay","pytorch","unity"],"latest_commit_sha":null,"homepage":null,"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/frgfm.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":"2019-11-12T23:45:57.000Z","updated_at":"2019-11-13T11:28:23.000Z","dependencies_parsed_at":"2023-04-22T18:04:25.346Z","dependency_job_id":null,"html_url":"https://github.com/frgfm/drlnd-p2-continuous-control","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frgfm%2Fdrlnd-p2-continuous-control","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frgfm%2Fdrlnd-p2-continuous-control/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frgfm%2Fdrlnd-p2-continuous-control/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frgfm%2Fdrlnd-p2-continuous-control/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/frgfm","download_url":"https://codeload.github.com/frgfm/drlnd-p2-continuous-control/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239727059,"owners_count":19687096,"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":["actor-critic","ddpg-algorithm","deep-reinforcement-learning","experience-replay","pytorch","unity"],"created_at":"2024-10-11T02:10:24.229Z","updated_at":"2025-12-31T19:30:24.768Z","avatar_url":"https://github.com/frgfm.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Reach out\n[![License](https://img.shields.io/badge/License-MIT-brightgreen.svg)](LICENSE) [![Codacy Badge](https://api.codacy.com/project/badge/Grade/1d6d58ddc5f4445492172f9b349668bc)](https://www.codacy.com/manual/fg/drlnd-p2-continuous-control?utm_source=github.com\u0026amp;utm_medium=referral\u0026amp;utm_content=frgfm/drlnd-p2-continuous-control\u0026amp;utm_campaign=Badge_Grade) [![CircleCI](https://circleci.com/gh/frgfm/drlnd-p2-continuous-control.svg?style=shield)](https://circleci.com/gh/frgfm/drlnd-p2-continuous-control)\n\nThis repository is an implementation of DDPG agent for the continuous control project of Udacity Deep Reinforcement Learning nanodegree, in the reacher environment provided by unity.\n\n![reacher-gif](https://video.udacity-data.com/topher/2018/June/5b1ea778_reacher/reacher.gif)\n\n\n\n## Table of Contents\n\n- [Environment](#environment)\n- [Getting Started](#getting-started)\n  - [Prerequisites](#prerequisites)\n  - [Installation](#installation)\n- [Usage](#usage)\n- [Credits](#credits)\n- [License](#license)\n\n\n\n## Environment\n\nIn this environment, a double-jointed arm can move to target locations. A reward of +0.1 is provided for each step that the agent's hand is in the goal location. Thus, the goal of your agent is to maintain its position at the target location for as many time steps as possible.\n\nThe observation space consists of 33 variables corresponding to position, rotation, velocity, and angular velocities of the arm. Each action is a vector with four numbers, corresponding to torque applicable to two joints. Every entry in the action vector should be a number between -1 and 1.\n\nThe task is episodic, and in order to solve the environment, your agent must get an average score of +30 over 100 consecutive episodes.\n\n\n\n## Getting started\n\n### Prerequisites\n\n- Python 3.6 (or more recent)\n- [pip](https://pip.pypa.io/en/stable/)\n- [ml-agents](https://github.com/Unity-Technologies/ml-agents) v0.4 (check this [release](https://github.com/Unity-Technologies/ml-agents/releases/tag/0.4.0b) if you encounter issues)\n\n### Installation\n\nYou can install the project requirements as follows:\n\n```shell\ngit clone https://github.com/frgfm/drlnd-p2-continuous-control.git\ncd drlnd-p2-continuous-control\npip install -r requirements.txt\n```\n\nDownload the environment build corresponding to your OS\n\n- Linux: [here](https://s3-us-west-1.amazonaws.com/udacity-drlnd/P2/Reacher/one_agent/Reacher_Linux.zip)\n- Mac OSX: [here](https://s3-us-west-1.amazonaws.com/udacity-drlnd/P2/Reacher/one_agent/Reacher.app.zip)\n- Windows (32-bit): [here](https://s3-us-west-1.amazonaws.com/udacity-drlnd/P2/Reacher/one_agent/Reacher_Windows_x86.zip)\n- Windows (64-bit): [here](https://s3-us-west-1.amazonaws.com/udacity-drlnd/P2/Reacher/one_agent/Reacher_Windows_x86_64.zip)\n\nThen extract the archive in the project folder.\n\n\n\nIf you wish to use the agent trained by repo owner, you can download the model parameters as follows:\n\n```shell\nwget https://github.com/frgfm/drlnd-p2-continuous-control/releases/download/v0.1.0/ddpg_actor.pt\n```\n\n\n\n## Usage\n\n### Training\n\nAll training arguments can be found using the `--help` flag:\n\n```shell\npython train.py --help\n```\n\nBelow you can find an example to train your agent:\n\n```shell\npython train.py --deterministic --no-graphics\n```\n\n### Evaluation\n\nYou can use an existing model's checkpoint to evaluate your agent as follows:\n\n```shell\npython evaluate.py --checkpoint ./ddpg_actor.pt\n```\n\n\n\n## Credits\n\nThis implementation is vastly based on the following papers:\n\n- [Asynchronous Actor Critic](https://arxiv.org/pdf/1602.01783.pdf)\n\n- [Proximal Policy Optimization](https://arxiv.org/pdf/1707.06347.pdf)\n- [DDPG](https://openreview.net/pdf?id=SyZipzbCb)\n\n\n\n## License\n\nDistributed under the MIT License. See `LICENSE` for more information.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffrgfm%2Fdrlnd-p2-continuous-control","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffrgfm%2Fdrlnd-p2-continuous-control","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffrgfm%2Fdrlnd-p2-continuous-control/lists"}