Build Deep Q-Network – Reinforcement Learning Code Project

21 thoughts on “Build Deep Q-Network – Reinforcement Learning Code Project”

1. Glad to see a new episode of this DQN series

2. 👉 Check out the blog post and other resources for this video:
   
   🔗 https://deeplizard.com/learn/video/PyQNfsGUnQA

3. 😍😍😍😍

4. Awesome videos guys, but I think you need to redo your branding and design.

5. Is the exploration and exploitation switch supposed to be a non-smooth transition?

6. My brain is just a DQN trained to write code to make DQN's that play cart pole.

7. Great video. it really helps me to implement DQN. I am very excited for the next video

8. yay my favorite playlist <3

9. Thank you for the content! I have a question. I'm trying to make my deep learning framework and as far as I know, fastai has part 2 of the part in deep learning where they frame everything from scratch. will the 2nd part of the course from fastai help me in creating the framework?

10. When is the next video coming I am excited for it.

11. Hello and thank you very much for that very interesting video. I have a question about the init function in the DQN class. I don't see the point to take the color into account (with this factor 3): can't we use the grey scaled versions of the screenshots ? Thank you in advance for your feedback ! I

12. I don’t have many experience in RL.
    I thought this video has remember some knowledge before.
    I don’t remember much knowledge before.But I happy to try how far I can get.

    What I learned:
    1、DQN structure is so simple. After I just learn the cnn series.
    2、Memory has capacity.If you continue push experience in memory . It may over-write the old one

    Question:
    1、Why always note the push number. After all the old one will be replaced. I thought maybe after video may tell us.

    Thank you for your great work. I personal think the RL will be the most important than others.

13. Again thanks for the excellent video series. Will you be able to add Deep Q Learning with Keras in either this RL series or in the Keras tutorial series ?

14. Should strategy be self.strategy?

15. Why you dont use grayscale images with 1 channel ? why you dont use Convolutional layers in your network ?

16. 10:33 min:
    Shouldn't it be: … that we don't have 50 experiences yet instead of 20?
    Since 20 are already in our replay-memory (memory []) ?

17. This is totally nuts! Loved it! 😂😂😂

18. ugh dumb question under import libraries the very first line of code does not work for me the python console says invalid syntax ?? in my code the % sign does not highlite. If I comment out this line the rest of the library stuff and the set up display work

19. Why is_ipython is False all the time? Can't plot the graph. Please help.

20. 15:04 i cant find the video mentioned, so i will just ask.
    with torch.no_grad() just disables the learning of the NN, right?

    Greedings from Germany.
    Keep it UP

21. In the Agent class select_action method, I am pretty sure it should be self.strategy instead of just strategy (14:12)

Comments are closed.