This is a concise Pytorch implementation of TD3(Twin Delayed DDPG) on continuous action space.
You can dircetly run 'TD3.py' in your own IDE.
python TD3.py
You can use the tensorboard to visualize the training curves, which are saved in the file 'runs'.
The rewards data are saved as numpy in the file 'data_train'.
[1] Zhang, J., Zhang, Q., Zhao, X., & Kan, J. (2022). Boosting denoisers with reinforcement learning for image restoration. Soft Computing, 26(7), 3261-3272.