{"id":25015774,"url":"https://github.com/m8nt0/frozenlake-q-learning-project","last_synced_at":"2025-03-30T06:29:34.282Z","repository":{"id":241249501,"uuid":"804677938","full_name":"m8nt0/FrozenLake-Q-Learning-Project","owner":"m8nt0","description":"demonstrates how to use Q-Learning to solve the FrozenLake environment from OpenAI Gym. It includes advanced features such as logging, configuration files, model saving/loading, plotting, and hyperparameter tuning.","archived":false,"fork":false,"pushed_at":"2024-05-23T04:21:19.000Z","size":8,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-05T08:37:18.733Z","etag":null,"topics":[],"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/m8nt0.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":"2024-05-23T03:53:16.000Z","updated_at":"2024-05-23T04:21:22.000Z","dependencies_parsed_at":"2024-05-23T05:25:05.502Z","dependency_job_id":"1cadc5e9-440f-4c8c-8e3b-bd7ffbc35aa7","html_url":"https://github.com/m8nt0/FrozenLake-Q-Learning-Project","commit_stats":null,"previous_names":["m8nt0/frozenlake-q-learning-project"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m8nt0%2FFrozenLake-Q-Learning-Project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m8nt0%2FFrozenLake-Q-Learning-Project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m8nt0%2FFrozenLake-Q-Learning-Project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m8nt0%2FFrozenLake-Q-Learning-Project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/m8nt0","download_url":"https://codeload.github.com/m8nt0/FrozenLake-Q-Learning-Project/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246285651,"owners_count":20752947,"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":[],"created_at":"2025-02-05T08:31:48.262Z","updated_at":"2025-03-30T06:29:34.265Z","avatar_url":"https://github.com/m8nt0.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FrozenLake-Q-Learning-Project\ndemonstrates how to use Q-Learning to solve the FrozenLake environment from OpenAI Gym. It includes advanced features such as logging, configuration files, model saving/loading, plotting, and hyperparameter tuning.\n\n## Requirements\n\n- Python 3.6+\n- numpy\n- gym\n- matplotlib\n- scikit-optimize\n- pyyaml\n\n## Project Structure\n\n- `configs/`: Contains configuration files.\n- `logs/`: Contains logs and saved data.\n- `models/`: Contains saved models.\n- `plots/`: Contains generated plots.\n- `src/`: Contains source code.\n\n## Setup\n\n1. **Install the required packages:**\n   ```bash\n   pip install -r requirements.txt\n\n## Instructions\n\n### Configure the Hyperparameters\n\nConfigure the hyperparameters in `configs/params.json`.\n\n### Run the Training Script\n\n    ```bash\n    python src/main.py --mode train\n\n## Run the Evaluation Script\n\n    ```bash\n    python src/main.py --mode evaluate\n\n## Configuration\n\n- **configs/config.json**: Contains environment and file paths configurations.\n- **configs/params.json**: Contains hyperparameters for the Q-Learning algorithm.\n\n## Logging and Plotting\n\n- Logs are saved in the `logs/` directory.\n- Training progress plots are saved in the `plots/` directory.\n\n## Advanced Features\n\n- **Logging**: Logs training progress to a file.\n- **Configuration Files**: Use JSON for environment and hyperparameter configurations.\n- **Model Saving and Loading**: Save and load the Q-table to and from a file.\n- **Plotting**: Generate plots for training rewards and episode lengths.\n- **Hyperparameter Tuning**: Supports basic hyperparameter tuning using a configuration file.\n\n## Example Usage\n\n### Training the Agent\n\nTo train the Q-Learning agent, run:\n\n    ```bash\n    python src/main.py --mode train\n\n## Evaluating the Agent\n\nTo evaluate the trained Q-Learning agent, run:\n\n    ```bash\n    python src/main.py --mode evaluate\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fm8nt0%2Ffrozenlake-q-learning-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fm8nt0%2Ffrozenlake-q-learning-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fm8nt0%2Ffrozenlake-q-learning-project/lists"}