Homepage - elsciRL

<div align="center" style="font-size:200%"> <p><b>Improve Any Reinforcement Learning Application with Language</b></p> </div> <div align="center" style="font-size:100%"> <p><i>Open-source Python library for Integrating Language Solutions & LLMs into any Reinforcement Learning Application</i></p> </div> <div class="card-grid" align = "center"> <div class="price"> <p><a target="_self" href="https://github.com/pdfosborne/elsciRL" class="button-63"> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512" width="16px"><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3 .3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5 .3-6.2 2.3zm44.2-1.7c-2.9 .7-4.9 2.6-4.6 4.9 .3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3 .7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3 .3 2.9 2.3 3.9 1.6 1 3.6 .7 4.3-.7 .7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3 .7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3 .7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"/></svg>&nbsp elsciRL Software </a></p> </div> <div class="price"> <p><a target="_self" href="https://github.com/pdfosborne/elsciRL-Wiki" class="button-63"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512" width="16px"><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3 .3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5 .3-6.2 2.3zm44.2-1.7c-2.9 .7-4.9 2.6-4.6 4.9 .3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3 .7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3 .3 2.9 2.3 3.9 1.6 1 3.6 .7 4.3-.7 .7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3 .7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3 .7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"/></svg>&nbsp elsciRL Wiki</a></p> </div> </div> <div align="center"> <img src="https://github.com/pdfosborne/elsciRL-Wiki/blob/main/Resources/images/elsciRL_GUI_GIF_2.gif?raw=true" /> </div> <div align="left" style="font-size:100%"> <p><b>Announcements</b></p> </div> <div align="left" style="font-size:75%"> <p>[14/07/2025] <b>New publication</b> <a href="https://arxiv.org/abs/2507.08705"><i>elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings</i></a></p> </div> --- <div align="center" style="font-size:150%"> <p><b>Features</b></p> </div> 1. **Enhance any Reinforcement Learning application with language.** 2. Our **Graphical User Interface (GUI)** makes it easy to apply the latest algorithms. 3. **Develop new applications faster** with fewer problem specific requirements. 4. **Accelerate your research** with our [Open-Source Wiki](https://github.com/pdfosborne/elsciRL-Wiki) and [Discord Server](https://discord.gg/GgaqcrYCxt) to share knowledge. 5. **Share your work with ease** using our *reproducibility features* such as configuration exporting. 6. **Collect user input data with ease** by using our GUI to let non-technical users provide instructions that guide the agent. <div align="center"> <img src="https://github.com/pdfosborne/elsciRL-Wiki/blob/main/Resources/images/Agent-Performance-2.gif?raw=true" /> </div> --- <div align="center" style="font-size:150%"> <p><b>Getting Started</b></p> </div> <div class="card-grid" align = "center"> <div class="price" > <p><a target="_self" href="https://elsci.org/App+Interface+Guide" class="button-63">First Time Setup</a></p> </div> <div class="price" align="center"> <p><a target="_self" href="https://elsci.org/Developer+Guide" class="button-63" >Developer Guide</a></p> </div> </div> <div align="center" style="font-size:100%"> <p><i>See more of the interface in action</i></p> </div> <div align="center"> <iframe width="400" height="300" src="https://www.youtube.com/embed/JbPtl7Sk49Y"> </iframe> </div> <div align="center" style="font-size:100%"> <p><i>Accelarate your research with our open-source Wiki</i></p> </div> <div align="center"> <a href="https://elsci.org/Docs+&+Wiki+Guide" class="button-63">Docs & Wiki guide</a> </div> ---- <div align="center" style="font-size:150%"> <p><b>What is elsciRL?</b></p> </div> **elsciRL (pronounced L-SEE)** offers a general purpose Python library for accelerating the development of language based Reinforcement Learning (RL) approaches. Our novel solution is a two-phased approach: 1. Adapters transforms the RL application with language 2. An unsupervised instruction following approach which allows a user input to guide the agent beyond the default reward signal These combine to define our **Explicit Language for Self-Completing Instruction** methodology, i.e. **elsci**. Our solution reduces the setup requirements and costs when introducing language to new applications that typically required significant amounts of human labelled data. The framework was formally defined in [my doctoral thesis](https://research.manchester.ac.uk/en/studentTheses/improving-real-world-reinforcement-learning-by-self-completing-hu) and has since been summarised in our [systems demonstration paper](https://arxiv.org/abs/2507.08705). <div align="center"> <img src="https://raw.githubusercontent.com/pdfosborne/elsciRL-Wiki/refs/heads/main/Resources/images/elsciRL_LLM_Overview-v2.png" /> </div> ---- <div align="center" style="font-size:150%"> <p><b>What is Reinforcement Learning?</b></p> </div> Reinforcement Learning is an Artificial Intelligence methodology that teaches machines how to make decisions and perform actions to achieve a goal. It's based on the idea that machines can learn from their experiences to automate a task without being told exactly what to do, similar to how humans learn through trial and error. See the [FAQs](https://elsci.org/FAQs) for more information. ---- **Quicklinks:** [About Us](https://elsci.org/About+us) | [FAQs](https://elsci.org/FAQs) | [New Developers](https://elsci.org/Developer+Guide) | [Contributing Guide](https://elsci.org/Become+a+Contributor) | [App Interface Guide](https://elsci.org/App+Interface+Guide) | [Using the Wiki](https://elsci.org/Docs+&+Wiki+Guide) <div id="sticky-button"> <a href="https://discord.gg/GgaqcrYCxt"><img src="https://raw.githubusercontent.com/pdfosborne/elsciRL-Wiki/refs/heads/main/Resources/images/discord_icon.png" width="50"></a> </div>