Reinforcement Learning Toolbox - How to implement Markov decision process (MDP) environment and DQN agent for image classification?
10 views (last 30 days)
Show older comments
We are working on creating an MDP environment using a DQN agent using the reinforcement learning toolbox. We used an imageDatastore command to store the input images for classification. Our question is how does the RL toolbox read the imported images and use them to train the DQN agent? What commands should we include and what should be the network achitecture of the DQN agent for image classification?
Attached below is the proposed network achitecture. However, there were errors generated when trained using DQN.
Thanks!
0 Comments
Answers (0)
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!