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.
- 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
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.
- 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
- 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
RLMatrix is licensed under the RLMatrix Comprehensive Dual License Agreement
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。
- 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
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。
- 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
- 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
RLMatrix采用RLMatrix综合双重许可协议