GitHub - PathumDilhara/RL-agent-for-CNN-hyper-parameter-optimization: A reinforcement learning (RL) based agent that automatically tunes hyperparameters (like learning rate, batch size, optimizer) for convolutional neural networks (CNNs) to maximize validation accuracy.

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
.gitignore		.gitignore
ENV_DATA.txt		ENV_DATA.txt
v1_modified_lenet_cnn.ipynb		v1_modified_lenet_cnn.ipynb
v2_rl_cnn_only_lr.ipynb		v2_rl_cnn_only_lr.ipynb
v3_rl_cnn_all.ipynb		v3_rl_cnn_all.ipynb

About

A reinforcement learning (RL) based agent that automatically tunes hyperparameters (like learning rate, batch size, optimizer) for convolutional neural networks (CNNs) to maximize validation accuracy.

reinforcement-learning artificial-intelligence q-learning-algorithm