This repository contains the following implementations:
-> binned read size throughput prediction (binning_main.py, real_large_data_processing.py, real_large_train.py)
-> throughput prediction on principal components (pca_predict_main.py, pca_utils.py, pca_new_set_generate.py)
-> throughput prediction using the encoder-decoder architecture (encoder_decoder_main.py)
-> Grid World problem implementation (dwave_boltzmann.py)
-> reinforcement learning (RL) framework for the quantum agent (QA) and the environment network (throughput prediction) (agent_main_2.py)
Notes:
-> To run parts of the code, make sure the paths in the files are consistent. A lot of the code has been run on remote machines which had different file paths.
-> There are multiple version of functions which solve the same issues. This is because once more data was available hardware constraints had to be overcome through optimization of the code.
Quantum agent paper: Free energy-based reinforcement learning using a quantum processor (https://arxiv.org/abs/1706.00074)