66 separate nns for throttle and direction#68
Open
schmidt1139 wants to merge 12 commits into63-troubleshoot-nn-setupfrom
Open
66 separate nns for throttle and direction#68schmidt1139 wants to merge 12 commits into63-troubleshoot-nn-setupfrom
schmidt1139 wants to merge 12 commits into63-troubleshoot-nn-setupfrom
Conversation
The user can choose from multiple loss functions, this just reports the selected loss function in the plot name instead of MSE.
The user can express if they would like just a u network training/eval, an alpha only network training, or all 3.
The user can express if they would like just a u network training/eval, an alpha only network training, or all 3.
The params dictionary was previously just used for holding non- dimensional parameters but now holds most of the simulation parameters. Updated name to reflect this.
(For example - a u only NN will not have alpha comparison data to plot)
If the user elects to train on BCE with logits loss, the NN will be trained to output the logits corresponding to the likelihood of firing the thruster. This extra code handles the transformation to a sigmoid probability and the control becomes 1 if the signal is greater than 0.5.
MartinAstro
approved these changes
Oct 30, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR contains the extra training scripts and utilities needed to conduct an experiment to train separate neural networks for bang-bang throttle control and thrust direction.