Open 1219-wangjindong opened 1 year ago
You can refer Hsieh, C.-K.; Chan, K.-L.; Chien, F.-T. Energy-Efficient Power Allocation and User Association in Heterogeneous Networks with Deep Reinforcement Learning. Appl. Sci. 2021, 11, 4135. https://doi.org/10.3390/app1109413.
I'm glad you were able to reply to my message, thank you for your answer, I have one more question, why does this path change to whatever is reported as an error? os.chdir('/home/chan/PDQN/')
I think that it may be caused by the file path in your environment. If you want to run the code, you need to ensure the code and the file path are the same.
Does this path represent the path where the code is stored?
Yes, you need to modify it.
Hello, I'm bothering you again. I have another problem with the code, the state of the reinforcement learning in the paper is the data rate, but there is no power assigned yet why would the data rate be used as the state and not the channel gain . Looking forward to your reply . Have a nice life.
I think it is not suitable to consider the channel gain as the state because the channel gain can not reflect the information about the power assigned. PDQN is an algorithm of RL. The agent in RL can interact with the environment to learn the policy to decide the action (power assigned). If you want to set the channel gain as the input of the neural network, I think you can prepare the label of the power assigned by other optimization algorithms and just use the deep neural network to solve the problem.
Could you please resend the link to the article? The link seems to be invalid.
Could you please resend the link to the article? The link seems to be invalid.
why not search it by the title,it is before the link
Excuse me, is there a paper on this code?