{"id":26384341,"url":"https://github.com/alkaifaftab000/autonomous-maze-solver","last_synced_at":"2026-04-12T17:53:02.090Z","repository":{"id":278914128,"uuid":"937061927","full_name":"alkaifaftab000/Autonomous-Maze-Solver","owner":"alkaifaftab000","description":"Building an Autonomous Maze Solver using reinforcement learning to train agents for decision-making in dynamic grid-based environments","archived":false,"fork":false,"pushed_at":"2025-03-16T08:13:47.000Z","size":3032,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-16T09:20:54.449Z","etag":null,"topics":["agent","criticism","cuda","gymnasium-environment","maze-solving-bot","pytorch","reinforcement-learning","reward-functions"],"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/alkaifaftab000.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":"2025-02-22T08:36:59.000Z","updated_at":"2025-03-16T08:15:53.000Z","dependencies_parsed_at":"2025-03-16T09:21:02.683Z","dependency_job_id":null,"html_url":"https://github.com/alkaifaftab000/Autonomous-Maze-Solver","commit_stats":null,"previous_names":["alkaifaftab000/project","alkaifaftab000/autonomous-maze-solver"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alkaifaftab000%2FAutonomous-Maze-Solver","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alkaifaftab000%2FAutonomous-Maze-Solver/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alkaifaftab000%2FAutonomous-Maze-Solver/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alkaifaftab000%2FAutonomous-Maze-Solver/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alkaifaftab000","download_url":"https://codeload.github.com/alkaifaftab000/Autonomous-Maze-Solver/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243989726,"owners_count":20379649,"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":["agent","criticism","cuda","gymnasium-environment","maze-solving-bot","pytorch","reinforcement-learning","reward-functions"],"created_at":"2025-03-17T07:23:01.932Z","updated_at":"2025-11-02T09:04:55.027Z","avatar_url":"https://github.com/alkaifaftab000.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Autonomous Maze Solver 🚀\n\n## Project Overview 🧩\nLeveraging the power of reinforcement learning, this project develops an **Autonomous Maze Solver** purely based on reinforcement learning principles.\n\n---\n\n## Workflows ⚙️\n1. **Creating `agent.py`**:  \n   - Controls the **actor** and **critic** functionalities.  \n   - Trains the system from previous mistakes using reward functions.\n\n2. **Creating `model.py`**:  \n   - The **actor** performs actions while the **critic** evaluates by giving punishments or rewards.\n     \n3. **Creating `gymnasium.py`**:  \n   - Develops grid structures for the maze environment.\n\n_Note: No traditional machine learning models were created._\n\n---\n\n## Learning Outcomes 🎓\n1. Developed a deeper understanding of reinforcement learning frameworks.  \n2. Acquired insights into implementing actor-critic models and reward-driven training systems.  \n\n---\n## UI\n![Description of the GIF](gify.gif)\n---\n## Plugins and Libraries Used 🛠️\n- `--extra-index-url https://download.pytorch.org/whl/cu118`\n- `torch`\n- `torchvision`\n- `torchaudio`\n- `gymnasium\u003e=0.29.0`\n- `matplotlib\u003e=3.10.0`\n- `gymnasium-robotics\u003e=1.3.0`\n- `pybullet\u003e=3.2.0`\n- `tensorboard\u003e=2.15.0`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falkaifaftab000%2Fautonomous-maze-solver","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falkaifaftab000%2Fautonomous-maze-solver","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falkaifaftab000%2Fautonomous-maze-solver/lists"}