-
thank you so much for nice job.
I want to implement one of the algorithms without gradient in this project and compare the results with the algorithms in this project such as actorcritic, dqn ,rei…
-
add boolean option to episoderunnner.
if true, than then add the last fitness to next observation for the brain.
-
long term goal: it should be easy to use this framework for others.
Currently this issue is not for specific implementation and instead for discussion about general ideas how to achieve that long…
-
```
What steps will reproduce the problem?
1.training mode
2.add new qlearning / neuroEvolution team
3.save/load
What is the expected output? What do you see instead?
I expect a file save with the …
-
This issue is not a specific todo. It's a place to gather idea for optimizers to implement next
https://github.com/ShawK91/Evolutionary-Reinforcement-Learning
ERL sieht sehr relevant aus. Wir …
-
**Description:**
I am experiencing an issue with the `problem.make_net` method. When I try to generate a trained network using the `center` parameter from the `searcher.status`, the method fails un…
Duxo updated
4 months ago
-
Članovi tima:
Petljanski Jovan SW-31/2018, grupa 2
Asistenti:
Aleksandar Lukić
Problem koji se rešava:
Treniranje agenta da preskače prepreke na putu
Algoritam:
NEAT - Neuroevolution of a…
-
TL;DR:
Fitness of individuals is decided by their rank in their generation but not by their rank across generations
In each generation after the training episodes are done we do the following:
…
-
`algorithm.py` and the optimizer-classes are a huge mess. This started because we followed the design patterns used in DEAP. This was fine in the beginning, when we used most parts of DEAP "as intende…
-
Dear ml5 community,
I'm submitting a new issue. Please see the details below.
## Background
@yining1023 and I have been awarded a mini grant from [COSA](https://www.du.edu/ahss/opensourcea…