ModelCompressionRL
FinRL
ModelCompressionRL | FinRL | |
---|---|---|
2 | 200 | |
0 | 2,782 | |
- | - | |
2.6 | 9.8 | |
over 1 year ago | over 2 years ago | |
Jupyter Notebook | Jupyter Notebook | |
- | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ModelCompressionRL
-
Requesting help with Custom Layers (Layer Subclassing) - Model fit builds the model again! [Keras]
I saw that the number of filters depends on the height, is the height the same for all images? I guess so since you say that moving the Conv2D to another layer fixes that problem. If my guess is right, the error is that when the model is being build, height is None and you are trying to divide None by a number. To solve this problem you have to get the shape using h = tf.shape(inputs)[1] as 0 is the batch dimension. As for getting the tf.concat as a layer. You can use tf.keras.layers.concatenate, it works the same as tf.concat, but it is a layer. I am using it in a layer that performs to parallel convolutions and then concatenates both convolutions. When I print the summary I only get the name of the layer, not the tf.concat as you mention. Search for the FireLayer class in my code
- Adding new block/inputs to non-sequential network
FinRL
What are some alternatives?
tensortrade - An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.
Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020 - Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy. ICAIF 2020. Please star. [Moved to: https://github.com/AI4Finance-Foundation/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020]
Deep-Hedging
FinRL - FinRL: Financial Reinforcement Learning. 🔥
FinRL-Library - Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance. NeurIPS 2020 & ICAIF 2021. 🔥 [Moved to: https://github.com/AI4Finance-Foundation/FinRL]
rl_lib - Series of deep reinforcement learning algorithms 🤖
FinRL-Trading - For trading. Please star.
FinanceOps - Research in investment finance with Python Notebooks
FinRL-Meta - FinRL-Meta: Dynamic datasets and market environments for FinRL.
Rubiks-Cube-Reinforcement-Learning - Solving a Rubik's Cube and 15 Puzzle using the Deep Reinforcement Learning and Search
hands-on-rl - Free course that takes you from zero to Reinforcement Learning PRO 🦸🏻🦸🏽