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.

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

NEAT: Neural Evolution through Augmented Topology #1105

Open
wants to merge 114 commits into
base: master
from

Conversation

Projects
None yet
3 participants
@kartik-nighania
Contributor

kartik-nighania commented Aug 27, 2017

this class was created by @BangLiu which implements a neural evolution technique.

The goal of this new PR is to bring a better platform to discuss and document the conversation that i have with my mentor about the changes and fixes that went through while debugging.

kartik-nighania added some commits Mar 14, 2017

kartik-nighania added some commits Aug 6, 2017

added files
removed cmaes files

cmaes files removed
@zoq

This comment has been minimized.

Show comment
Hide comment
@zoq

zoq Aug 28, 2017

Member

Nice commit message :)

Member

zoq commented Aug 28, 2017

Nice commit message :)

@sourabhvarshney111

This comment has been minimized.

Show comment
Hide comment
@sourabhvarshney111

sourabhvarshney111 Mar 17, 2018

Contributor

@kartik-nighania I am not sure whether this is complete or not. @zoq probably this can be merged.

Contributor

sourabhvarshney111 commented Mar 17, 2018

@kartik-nighania I am not sure whether this is complete or not. @zoq probably this can be merged.

@zoq

This comment has been minimized.

Show comment
Hide comment
@zoq

zoq Mar 17, 2018

Member

We encountered an issue were for some tasks, the population doesn't change/evolve after a number of iterations, I think IsSameSpecies does something strange since we end up with a single genome.

Member

zoq commented Mar 17, 2018

We encountered an issue were for some tasks, the population doesn't change/evolve after a number of iterations, I think IsSameSpecies does something strange since we end up with a single genome.

@sourabhvarshney111

This comment has been minimized.

Show comment
Hide comment
@sourabhvarshney111

sourabhvarshney111 Mar 17, 2018

Contributor

@zoq Is that the only problem. If that is only problem, I would try to go through the code and try to figure out the issue.

Contributor

sourabhvarshney111 commented Mar 17, 2018

@zoq Is that the only problem. If that is only problem, I would try to go through the code and try to figure out the issue.

@zoq

This comment has been minimized.

Show comment
Hide comment
@zoq

zoq Mar 17, 2018

Member

If I remember right yes, I think the first step would be to reproduce the issue, let me know if you need any help.

Member

zoq commented Mar 17, 2018

If I remember right yes, I think the first step would be to reproduce the issue, let me know if you need any help.

@sourabhvarshney111

This comment has been minimized.

Show comment
Hide comment
@sourabhvarshney111

sourabhvarshney111 Mar 17, 2018

Contributor

Any idea when this issue used to occur @zoq because I don't have any idea regarding that.

Contributor

sourabhvarshney111 commented Mar 17, 2018

Any idea when this issue used to occur @zoq because I don't have any idea regarding that.

@zoq

This comment has been minimized.

Show comment
Hide comment
@zoq

zoq Mar 17, 2018

Member

We used the mario task, but I think you could also use the XOR task to reproduce the issue.

Member

zoq commented Mar 17, 2018

We used the mario task, but I think you could also use the XOR task to reproduce the issue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment