{"id":16992062,"url":"https://github.com/jolares/deep-reinforcement-learning-navigation","last_synced_at":"2026-04-13T23:33:32.965Z","repository":{"id":39724328,"uuid":"271111145","full_name":"jolares/deep-reinforcement-learning-navigation","owner":"jolares","description":null,"archived":false,"fork":false,"pushed_at":"2023-03-25T00:13:15.000Z","size":27475,"stargazers_count":0,"open_issues_count":2,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-22T04:13:02.638Z","etag":null,"topics":["deep-reinforcement-learning","dqn","pytorch"],"latest_commit_sha":null,"homepage":"","language":"ASP","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/jolares.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":"2020-06-09T21:13:53.000Z","updated_at":"2020-10-05T03:19:02.000Z","dependencies_parsed_at":"2024-11-28T13:37:13.806Z","dependency_job_id":null,"html_url":"https://github.com/jolares/deep-reinforcement-learning-navigation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jolares/deep-reinforcement-learning-navigation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jolares%2Fdeep-reinforcement-learning-navigation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jolares%2Fdeep-reinforcement-learning-navigation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jolares%2Fdeep-reinforcement-learning-navigation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jolares%2Fdeep-reinforcement-learning-navigation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jolares","download_url":"https://codeload.github.com/jolares/deep-reinforcement-learning-navigation/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jolares%2Fdeep-reinforcement-learning-navigation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31775913,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T20:17:16.280Z","status":"ssl_error","status_checked_at":"2026-04-13T20:17:08.216Z","response_time":93,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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","dqn","pytorch"],"created_at":"2024-10-14T03:28:11.794Z","updated_at":"2026-04-13T23:33:32.949Z","avatar_url":"https://github.com/jolares.png","language":"ASP","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Dueling Double DQN (D3QN) Learning: \u003cbr\u003e Collecting the Ripe Bananas\n\n\nTODO: GIF of trained Agent next to Plot of Rewards per episode \u0026 avg reward per episode\n\nThis project's goal is to implement an agent capable of learning navigation in a large grid-world environment\u003cbr\u003e\nas it also learns how to identify ripe bananas from reading raw-pixel data real-time and maximize the number it\ncan collect in a given time frame.\n\nFor the time being, this is a living document listing some of the project's specifications.\n\n## The problem\n\nTODO\n\n## The Environment\n\nTODO\n\n## Markov Decision Process (MDP)\n\n\n* TODO: state and action spaces\n* TODO:Consideration of environment-solved\n\n## Implementation Details\n\nThe report (Report.ipynb) describes:\n* TODO: The D3QN learning algorithm and chosen hyperparameters\n* TODO: The model neural networks architecture\n* TODO: Future ideas for improving the agent's performance.\n\n\n## Running the Project\n\nTODO:\n\n### Software Dependencies \u0026 Installation\n\n* Python 3\n* PyTorch\n* Numpy\n\n\n## Resources\n\n[Deep Reinforcement Learning with Double Q-learning](https://arxiv.org/abs/1509.06461)\n\n[Dueling Network Architectures for Deep Reinforcement Learning](https://arxiv.org/abs/1511.06581)\n\n[Prioritized Experience Replay](https://arxiv.org/pdf/1511.05952v4.pdf)\n\n[Reinforcement Learning (Sutton \u0026 Barto, 2020)](http://incompleteideas.net/book/RLbook2020.pdf)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjolares%2Fdeep-reinforcement-learning-navigation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjolares%2Fdeep-reinforcement-learning-navigation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjolares%2Fdeep-reinforcement-learning-navigation/lists"}