[Improve] - Pytorch Reinforcement DQN Tutorial #3080
Labels
docathon-h1-2025
A label for the docathon in H1 2025
medium
Reinforcement Learning
Issues relating to reinforcement learning tutorials
Uh oh!
There was an error while loading. Please reload this page.
🚀 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
cc @vmoens @nairbv
The text was updated successfully, but these errors were encountered: