这是indexloc提供的服务，不要输入任何密码
Skip to content

Dueling DQN #170

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 21 commits into from
Jul 29, 2020
Merged

Dueling DQN #170

merged 21 commits into from
Jul 29, 2020

Conversation

yingchengyang
Copy link
Contributor

@yingchengyang yingchengyang commented Jul 28, 2020 •
edited
Loading

  • I have marked all applicable categories:
    • exception-raising fix
    • algorithm implementation fix
    • documentation modification
    • new feature
  • If applicable, I have mentioned the relevant/related issue(s)

Less important but also useful:

  • I have visited the source website
  • I have searched through the issue tracker for duplicates
  • I have mentioned version numbers, operating system and environment, where applicable: 
    import tianshou, torch, sys
print(tianshou.__version__, torch.__version__, sys.version, sys.platform)

@yingchengyang yingchengyang changed the title Add files via upload Dual DQN Jul 28, 2020
@Trinkle23897 Trinkle23897 changed the title Dual DQN WIP: Dual DQN Jul 28, 2020
@Trinkle23897 Trinkle23897 changed the title WIP: Dual DQN WIP: Dueling DQN Jul 28, 2020
@Trinkle23897
Copy link
Collaborator

Trinkle23897 commented Jul 28, 2020 •
edited
Loading

Should be okay now, please have a check.
I also change the tic-tac-toe's hyperparameter since gamma=0.1 is quite unstable with Q-value noise.

@Trinkle23897 Trinkle23897 changed the title WIP: Dueling DQN Dueling DQN Jul 28, 2020
youkaichao
youkaichao reviewed Jul 29, 2020
View reviewed changes
duburcqa
duburcqa reviewed Jul 29, 2020
View reviewed changes
duburcqa
duburcqa previously approved these changes Jul 29, 2020
View reviewed changes
youkaichao
youkaichao reviewed Jul 29, 2020
View reviewed changes
@Trinkle23897 Trinkle23897 merged commit 99a1d40 into thu-ml:dev Jul 29, 2020
@Trinkle23897 Trinkle23897 linked an issue Jul 29, 2020 that may be closed by this pull request
Why is dqn playing breakout so bad? I trained 400 epochs and the final result did not exceed 6 points. #54
Closed
@Trinkle23897 Trinkle23897 added enhancement Feature that is not a new algorithm or an algorithm enhancement and removed enhancement Feature that is not a new algorithm or an algorithm enhancement labels Aug 6, 2020
BFAnas pushed a commit to BFAnas/tianshou that referenced this pull request May 5, 2024
@yingchengyang @Trinkle23897
Dueling DQN (thu-ml#170)
395d361 
Co-authored-by: n+e <463003665@qq.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Trinkle23897 Trinkle23897 Trinkle23897 approved these changes

@youkaichao youkaichao youkaichao approved these changes

@duburcqa duburcqa duburcqa left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Why is dqn playing breakout so bad? I trained 400 epochs and the final result did not exceed 6 points.
4 participants
@yingchengyang @Trinkle23897 @duburcqa @youkaichao