Skip to content

[Improve] - Pytorch Reinforcement DQN Tutorial #3080

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
Open
JDRanpariya opened this issue Oct 7, 2024 · 1 comment
Open

[Improve] - Pytorch Reinforcement DQN Tutorial #3080

JDRanpariya opened this issue Oct 7, 2024 · 1 comment
Labels
Reinforcement Learning Issues relating to reinforcement learning tutorials rl Issues related to reinforcement learning tutorial, DQN, and so on

Comments

@JDRanpariya
Copy link

JDRanpariya commented Oct 7, 2024 •
edited by pytorch-bot bot
Loading

🚀 Describe the improvement or the new tutorial

In current tutorial DQN is not performing well even after 600 episodes. I would like to update hyper parameters, so it reaches optimal policy by the end of training.

Following parameters needs to change and need to replace the Result image.

EPS_START = 1.0
EPS_END = 0
EPS_DECAY = 1500
LR = 5e-4

Existing tutorials on this topic

No response

Additional context

image

cc @vmoens @nairbv
@JDRanpariya JDRanpariya changed the title 💡 [Improve] - Pytorch Reinforcement Cart-pole Tutorial [IMPROVE] - Pytorch Reinforcement Cart-pole Tutorial Oct 7, 2024
@JDRanpariya JDRanpariya changed the title [IMPROVE] - Pytorch Reinforcement Cart-pole Tutorial [Improve] - Pytorch Reinforcement Cart-pole Tutorial Oct 7, 2024
@JDRanpariya JDRanpariya changed the title [Improve] - Pytorch Reinforcement Cart-pole Tutorial [Improve] - Pytorch Reinforcement DQN Tutorial Oct 7, 2024
@svekars svekars added Reinforcement Learning Issues relating to reinforcement learning tutorials rl Issues related to reinforcement learning tutorial, DQN, and so on labels Apr 16, 2025
@vmoens
Copy link
Contributor

vmoens commented Apr 17, 2025

Sounds good, feel free to propose a PR with these changes!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Reinforcement Learning Issues relating to reinforcement learning tutorials rl Issues related to reinforcement learning tutorial, DQN, and so on
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@svekars @vmoens @JDRanpariya