{"id":20122573,"url":"https://github.com/gabryv00/dqn_ros","last_synced_at":"2025-03-02T20:24:46.831Z","repository":{"id":223713800,"uuid":"750274685","full_name":"GabryV00/DQN_ROS","owner":"GabryV00","description":"Reinforcement Learning for Robot Navigation with ROS and Gazebo","archived":false,"fork":false,"pushed_at":"2024-02-22T15:12:39.000Z","size":9559,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-13T07:31:18.112Z","etag":null,"topics":["dqn","gazebo","reinforcement-learning","ros","turtlebot3"],"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/GabryV00.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-01-30T10:28:06.000Z","updated_at":"2025-01-07T09:01:37.000Z","dependencies_parsed_at":"2024-11-13T19:39:11.173Z","dependency_job_id":"e229a06c-594b-4aa7-a5ae-319cde1f1242","html_url":"https://github.com/GabryV00/DQN_ROS","commit_stats":null,"previous_names":["gabryv00/dqn_ros"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GabryV00%2FDQN_ROS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GabryV00%2FDQN_ROS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GabryV00%2FDQN_ROS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GabryV00%2FDQN_ROS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GabryV00","download_url":"https://codeload.github.com/GabryV00/DQN_ROS/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241565984,"owners_count":19983218,"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":["dqn","gazebo","reinforcement-learning","ros","turtlebot3"],"created_at":"2024-11-13T19:39:06.163Z","updated_at":"2025-03-02T20:24:46.803Z","avatar_url":"https://github.com/GabryV00.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Robot Navigation with Reinforcement Learning with ROS and Gazebo\n\nThis repository contains the files for the execution of a Reinforcement Learning algorithm, i.e. the Deep Q-Learning algorithm, for the navigation of a robot, the TurtleBot3, in a simulated environment in Gazebo, using ROS.\n\n## Architecture\n\nThe project consists of the following files:\n- `src/my_turtlebot3_openai_example/scripts/start_deepqlearning.py` which is the main file that contains the details of the DQN architecture, all the calls to the OpenAI ROS library and the function for saving the data\n- `src/my_turtlebot3_openai_example/config/my_turtlebot3_openai_deepqlearn_params.yaml` which contains all the parameters for the DQN architecture\n- `src/openai_ros/src/openai_ros/task_envs/turtlebot3/config/turtlebot3_world.yaml` which contains parameters related to the TurtleBot3 enviroment\n- `training_results/` contains the folder related to all the experiments conducted. Each folder contains:\n  * `plot.png` image containing the three plots relating to cumulative reward and total time, with the data not normalized\n  * `plot-std.png` image containing the three plots relating to cumulative reward and total time, with the normalized data\n  * `results-date.json` file containing all the parameters used in the experiment, plus the results obtained\n\n## Documentation\n\nThe project contains also `RobotControl_slides.pdf` which is a presentation that describe that work done in this project\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgabryv00%2Fdqn_ros","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgabryv00%2Fdqn_ros","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgabryv00%2Fdqn_ros/lists"}