RLMatrixNoMC 0.4.3.11

🚀 RLMatrix - Advanced Reinforcement Learning in C#

RLMatrix provides a comprehensive reinforcement learning framework for C# developers with performance exceeding Python alternatives. Built with TorchSharp, RLMatrix offers a type-safe, high-performance environment for developing and deploying reinforcement learning solutions.

💬 Get in Touch

• Discord: Join our community server for discussions, support, and updates
• GitHub Issues: Report bugs or request features through our GitHub issues
• Email: For business inquiries, contact adrian@sieradzki.io

🏁 Getting Started

Please visit our official documentation for the most up-to-date getting started guides and tutorials.

⚠️ Note: The examples in this repository are being updated. For more current examples, check out our testing repository.

✨ Key Features

• Comprehensive Algorithm Library: Includes PPO, DQN with all popular modifications (up to C51 and DQN Rainbow), GAIL, and more algorithms on the way
• Revolutionary DRL Workflow: Thanks to C# source generation in the toolkit, you can focus on your domain problem rather than wrestling with complex API requirements
• Multi-Head Support: Handle continuous, discrete, and mixed action spaces simultaneously in a single agent
• RNN Integration: Enable recurrent neural networks with a simple option toggle for sequential or partial observability problems
• Pure C# Implementation: Built entirely in C# with TorchSharp backend, providing native performance and complete type safety
• Game Engine Ready: Battle-tested in Unity and Godot
• Superior Performance: Faster and more stable than Python's stable-baselines, ml-agents, and Godot RL agents
• Multi-Environment Training: Scale learning across parallel (optionally networked) environments
• Real-time Monitoring: Built-in dashboard for visualizing training metrics
• Industrial-Grade Distributed Training: High-performance, fault-tolerant networked architecture ready for large-scale reinforcement learning deployments
• Transparent Source Code: Clean, well-documented codebase that's easy to extend or customize

🗺️ Roadmap

• Improve documentation and examples
• Expand algorithm library with additional state-of-the-art methods
• Further enhance Godot and Unity integration
• Add more tools for imitation learning and GAIL
• Test and optimize support for non-Windows non-CUDA platforms
• Streamline inference and deployment workflows

📄 License

RLMatrix is licensed under the RLMatrix Comprehensive Dual License Agreement

🚀 RLMatrix - C#中的高级强化学习

RLMatrix为C#开发者提供了一个全面的强化学习框架，其性能超越了Python替代方案。使用TorchSharp构建，RLMatrix提供了一个类型安全、高性能的环境，用于开发和部署强化学习解决方案。

💬 联系我们

• Discord: 加入我们的社区服务器进行讨论、获取支持和更新
• GitHub Issues: 通过GitHub issues报告错误或请求新功能
• 电子邮件: 商务咨询，请联系 adrian@sieradzki.io

🏁 开始使用

请访问我们的官方文档获取最新的入门指南和教程。

⚠️ 注意: 此代码库中的示例正在更新中。要获取更多当前示例，请查看我们的测试代码库。

✨ 主要特点

• 全面的算法库: 包括PPO、DQN及其所有流行的修改版本（最高可达C51和DQN Rainbow）、GAIL，以及更多即将推出的算法
• 革命性的DRL工作流: 得益于工具包中的C#源代码生成功能，您可以专注于领域问题，而不必纠结于复杂的API要求
• 多头支持: 在单个智能体中同时处理连续、离散和混合动作空间
• RNN集成: 通过简单的选项开关启用递归神经网络，以处理顺序或部分可观察性问题
• 纯C#实现: 完全使用C#构建，搭配TorchSharp后端，提供原生性能和完整的类型安全性
• 游戏引擎就绪: 在Unity和Godot中经过实战测试
• 卓越性能: 比Python的stable-baselines、ml-agents和Godot RL agents更快速和稳定
• 多环境训练: 通过并行（可选网络化）环境扩展学习
• 实时监控: 内置仪表板用于可视化训练指标
• 工业级分布式训练: 高性能、容错网络架构，为大规模强化学习部署做好准备
• 透明源代码: 干净、文档齐全的代码库，易于扩展或自定义

🗺️ 路线图

• 改进文档和示例
• 扩展算法库，增加更多最先进的方法
• 进一步增强Godot和Unity集成
• 添加更多用于模仿学习和GAIL的工具
• 测试和优化对非Windows非CUDA平台的支持
• 简化推理和部署工作流

📄 许可证

RLMatrix采用RLMatrix综合双重许可协议