Grow Open Source Bounties Hackathons Grants Codefund Quests Kudos
Back to Grants

TensorTrade: Trade Efficiently with Reinforcement Learning





0 contributors

Your contribution goes a long way!

1 DAI contribution

+ 0 DAI match

10 DAI contribution

+ 0 DAI match

100 DAI contribution

+ 0 DAI match

1,000 DAI contribution

+ 0 DAI match

Next update : 1 month, 3 weeks ago | Last updated : 1 month, 3 weeks ago


{"ops":[{"attributes":{"background":"#f8fafc","color":"#9b59b6","link":"https://github.com/notadamking/tensortrade"},"insert":"TensorTrade"},{"insert":" is an open source Python framework for building, training, evaluating, and deploying robust trading algorithms using reinforcement learning. The framework focuses on being highly composable and extensible, to allow the system to scale from simple trading strategies on a single CPU, to complex investment strategies run on a distribution of HPC machines.\n\nUnder the hood, the framework uses many of the APIs from existing machine learning libraries to maintain high quality data pipelines and learning models. One of the main goals of TensorTrade is to enable fast experimentation with algorithmic trading strategies, by leveraging the existing tools and pipelines provided by "},{"attributes":{"background":"#ffffff","color":"#e74c3c","code":true},"insert":"numpy"},{"insert":", "},{"attributes":{"background":"#ffffff","color":"#e74c3c","code":true},"insert":"pandas"},{"insert":", "},{"attributes":{"background":"#ffffff","color":"#e74c3c","code":true},"insert":"gym"},{"insert":", "},{"attributes":{"background":"#ffffff","color":"#e74c3c","code":true},"insert":"keras"},{"insert":", and "},{"attributes":{"background":"#ffffff","color":"#e74c3c","code":true},"insert":"tensorflow"},{"insert":".\n\nEvery piece of the framework is split up into re-usable components, allowing you to take advantage of the general use components built by the community, while keeping your proprietary features private. The aim is to simplify the process of testing and deploying robust trading agents using deep reinforcement learning, to allow you and I to focus on creating profitable strategies.\n\n"},{"attributes":{"italic":true},"insert":"The goal of this framework is to enable fast experimentation, while maintaining production-quality data pipelines."},{"insert":"\n\n"},{"attributes":{"bold":true},"insert":"Guiding principles"},{"attributes":{"header":1},"insert":"\n"},{"attributes":{"italic":true},"insert":"Inspired by"},{"insert":" "},{"attributes":{"color":"#9b59b6","link":"https://github.com/keras-team/keras"},"insert":"Keras’ guiding principles"},{"insert":".\n\n"},{"attributes":{"italic":true},"insert":"User friendliness."},{"insert":" TensorTrade is an API designed for human beings, not machines. It puts user experience front and center. TensorTrade follows best practices for reducing cognitive load: it offers consistent & simple APIs, it minimizes the number of user actions required for common use cases, and it provides clear and actionable feedback upon user error.\n\n"},{"attributes":{"italic":true},"insert":"Modularity."},{"insert":" A trading environment is a conglomeration of fully configurable modules that can be plugged together with as few restrictions as possible. In particular, instrument exchanges, feature pipelines, action strategies, reward strategies, trading agents, and performance reports are all standalone modules that you can combine to create new trading environments.\n\n"},{"attributes":{"italic":true},"insert":"Easy extensibility."},{"insert":" New modules are simple to add (as new classes and functions), and existing modules provide ample examples. To be able to easily create new modules allows for total expressiveness, making TensorTrade suitable for advanced research and production use.\n\nView the "},{"attributes":{"link":"http://www.tensortrade.org/en/latest/"},"insert":"documentation"},{"insert":" or the "},{"attributes":{"link":"https://github.com/notadamking/tensortrade"},"insert":"Github"},{"insert":".\n\n"},{"attributes":{"background":"#fcfcfc","color":"#9b59b6","link":"https://github.com/notadamking/tensortrade"},"insert":"Feel free to also walk through the "},{"attributes":{"color":"#9b59b6","link":"https://medium.com/@notadamking/trade-smarter-w-reinforcement-learning-a5e91163f315"},"insert":"Medium tutorial"},{"insert":".\n\n\n\n"}]}

Activity Feed