Most modern trading algorithms are dominated by CNNs and LSTMs.
LSTM is suitable for processing time series data.
However, as CNNs became more adept at identifying patterns in charts, the two algorithms became dominant.
This algorithm aims to utilize the advantages of both models by processing time series using the POMDP definition of DQN and identifying patterns using CNN.
Python 3.8 (for dataclass support) or higher is required.
pip install -r requirements.txt
or
pip install h5py
pip install keras
download from HERE
