-
There are a few different configurations for evolution strategies. Here are some of the use cases I came up with. The first one results in maximally efficient trainer xp, the second results in evolved…
-
Currently Backtrader performs a grid search to optimize strategy parameters by running through all possible parameters configurations. More complex strategies would benefit from applying more advanced…
-
Appreciate this excellent work. I got a lot of inspiration from this work.
I have achieved to train an AI for a more difficult version flappy bird: the horizontal distance between adjacent pipes an…
-
At some point we thinking about having reinforcement learning and/or neuro-evolution-style reinforcement learning examples in ml5. Some references:
With Genetic Algorithms and vanilla JS neural net…
-
https://cs.stanford.edu/people/jure/pubs/sampling-kdd06.pdf
-
Perhaps from https://graphics.stanford.edu/~mdfisher/DominionAI.html
Maybe try an engine AI
-
This issue captures our rationale/implementation for the reproducing aspect of the general agent.
tl;dr
- General agent can now spawn children, with a separate prompt and potentially balance
To…
-
- Abstract (2-3 lines)
As with many fields, applications of machine learning and computational methods are expanding to the financial world too. Modelling financial markets is a challenging area desp…
-
Gradually thinking some renaming of functions, files, classes will help make the material more accessible. For example:
Variables and functions:
- [ ] `height` -> `individual_size` (#223)
- [x]…
-
Hello everyone,
I am looking to create a genotype for solving production batch-sizing problem using evolutionary strategies
The genotype has 2 genes: One gene representing the batch size and anoth…