I hope you are doing well. I am always grateful to you for your kind response. It took me quite some time to actually implement this algorithm on experimental system. I am truly indebted to you.
I am glad to share that I am continue to work on your repository. In particular, I want to extend your work and implement PPO, TRPO and Imitation learning. Could you please guide me where should I makes change to shift from SAC to these algorithms? Thank you.
Next question is related to current algorithm i.e. SAC. I am wondering how I can download important parameters which describe the convergance of SAC algorithm such as commulative reward, actor loss and critic loss.
Dear @masato-ka ,
I hope you are doing well. I am always grateful to you for your kind response. It took me quite some time to actually implement this algorithm on experimental system. I am truly indebted to you.
I am glad to share that I am continue to work on your repository. In particular, I want to extend your work and implement PPO, TRPO and Imitation learning. Could you please guide me where should I makes change to shift from SAC to these algorithms? Thank you.
Next question is related to current algorithm i.e. SAC. I am wondering how I can download important parameters which describe the convergance of SAC algorithm such as commulative reward, actor loss and critic loss.
Thank you for your help and teaching me.