{"id":28484385,"url":"https://github.com/kingdrea/rpg","last_synced_at":"2025-08-17T10:02:59.547Z","repository":{"id":296472465,"uuid":"993467158","full_name":"kingdrea/RPG","owner":"kingdrea","description":"RPG offers a clear framework for developing KL-regularized policy gradient methods in online reinforcement learning. This repository includes tools for data preparation and the RLHF process, making it easier to implement the concepts from our research. 🛠️📚","archived":false,"fork":false,"pushed_at":"2025-07-05T23:14:49.000Z","size":8693,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-06T00:20:47.361Z","etag":null,"topics":["angband","application","canvas","combat","composer","flutter","game-engine","godot","hacktoberfest","laravel","roguelike","turn-based","tutorial","ultima-online","unity","unreal-engine","web","webgame"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":false,"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/kingdrea.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,"zenodo":null}},"created_at":"2025-05-30T21:00:02.000Z","updated_at":"2025-07-05T23:14:52.000Z","dependencies_parsed_at":"2025-07-06T00:29:35.808Z","dependency_job_id":null,"html_url":"https://github.com/kingdrea/RPG","commit_stats":null,"previous_names":["kingdrea/rpg"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/kingdrea/RPG","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kingdrea%2FRPG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kingdrea%2FRPG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kingdrea%2FRPG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kingdrea%2FRPG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kingdrea","download_url":"https://codeload.github.com/kingdrea/RPG/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kingdrea%2FRPG/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270831768,"owners_count":24653412,"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","status":"online","status_checked_at":"2025-08-17T02:00:09.016Z","response_time":129,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["angband","application","canvas","combat","composer","flutter","game-engine","godot","hacktoberfest","laravel","roguelike","turn-based","tutorial","ultima-online","unity","unreal-engine","web","webgame"],"created_at":"2025-06-07T22:06:50.935Z","updated_at":"2025-08-17T10:02:59.321Z","avatar_url":"https://github.com/kingdrea.png","language":"Python","readme":"# RPG: Regularized Policy Gradient Implementation 🎮\n\n![RPG Logo](https://img.shields.io/badge/RPG-Regularized_Policy_Gradient-blue.svg)\n![GitHub Releases](https://img.shields.io/badge/Releases-latest-orange.svg)\n\nWelcome to the official implementation of Regularized Policy Gradient (RPG). This repository contains the code and resources necessary to understand and utilize RPG in various reinforcement learning scenarios. You can find the original paper [here](https://arxiv.org/abs/2505.17508).\n\n## Table of Contents\n\n- [Introduction](#introduction)\n- [Features](#features)\n- [Installation](#installation)\n- [Usage](#usage)\n- [Examples](#examples)\n- [Contributing](#contributing)\n- [License](#license)\n- [Contact](#contact)\n\n## Introduction\n\nReinforcement learning has gained significant traction in recent years, particularly in complex environments. The Regularized Policy Gradient (RPG) method introduces a novel approach to enhance the stability and performance of policy gradient methods. By applying regularization techniques, RPG improves learning efficiency and reduces variance, making it suitable for large-scale applications.\n\n## Features\n\n- **Deep Learning Integration**: Leverage the power of deep learning frameworks for scalable training.\n- **Foundation Models**: Utilize pre-trained models to enhance learning.\n- **Post-Training Adaptation**: Adapt the model after initial training to improve performance.\n- **Reinforcement Learning Techniques**: Implement state-of-the-art RL methods.\n- **Large Language Models**: Incorporate LLMs for advanced decision-making.\n\n## Installation\n\nTo get started with RPG, follow these steps:\n\n1. Clone the repository:\n\n   ```bash\n   git clone https://github.com/kingdrea/RPG.git\n   cd RPG\n   ```\n\n2. Install the required dependencies:\n\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n3. For detailed instructions, please refer to the [Releases section](https://github.com/kingdrea/RPG/releases). Download the latest release, and execute the provided scripts to set up your environment.\n\n## Usage\n\nTo use RPG in your projects, follow these steps:\n\n1. Import the necessary modules:\n\n   ```python\n   from rpg import RPGAgent\n   ```\n\n2. Initialize the agent with your environment:\n\n   ```python\n   agent = RPGAgent(env)\n   ```\n\n3. Train the agent:\n\n   ```python\n   agent.train(episodes=1000)\n   ```\n\n4. Evaluate the agent's performance:\n\n   ```python\n   agent.evaluate()\n   ```\n\nFor more detailed usage instructions, please check the documentation within the repository.\n\n## Examples\n\nWe provide several examples to help you get started with RPG. You can find them in the `examples` directory. Here are a few key examples:\n\n- **CartPole**: A classic reinforcement learning environment. This example demonstrates how to balance a pole on a moving cart using RPG.\n- **Atari Games**: Use RPG to play Atari games like Breakout and Space Invaders. This showcases the capability of RPG in complex environments.\n- **Custom Environments**: Learn how to implement RPG in your custom environments.\n\nTo run an example, use the following command:\n\n```bash\npython examples/cartpole.py\n```\n\n## Contributing\n\nWe welcome contributions to the RPG project. To contribute, please follow these steps:\n\n1. Fork the repository.\n2. Create a new branch for your feature or bug fix.\n3. Make your changes and commit them.\n4. Push your changes to your forked repository.\n5. Create a pull request to the main repository.\n\nPlease ensure your code follows the existing style and includes appropriate tests.\n\n## License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details.\n\n## Contact\n\nFor any questions or issues, please open an issue on GitHub or contact the maintainers directly. You can also check the [Releases section](https://github.com/kingdrea/RPG/releases) for updates and new features.\n\n---\n\nThank you for your interest in RPG! We hope you find this implementation helpful in your reinforcement learning projects.","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkingdrea%2Frpg","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkingdrea%2Frpg","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkingdrea%2Frpg/lists"}