This is really great for beginners! Keep it up. I would love to see other games and configurations for the algorithm and how they could affect the simulation e.g. faster training time etc.
(Reward function = score function = fitness function) Basicly all the same, and they are just to tell the algorithm if it was a bad neural network, or a good little neurie :)
"more of a lucky coincidence than a well thought out strategy" Or as it's called when Space-X boosters use this exact strategy intentionally in real life, a "suicide burn".
the production quality is amazing, wow!
This is really great for beginners! Keep it up. I would love to see other games and configurations for the algorithm and how they could affect the simulation e.g. faster training time etc.
Wonderful explanation, keep making videos it’s really helpful for beginners
Really great visuals, sad it has so small amount of views
Now try dense multilayer NN, and evolve it using CMA-ES algorithm, and you will be surprised how fast it will converge.
Amazing explanations!
Great explaination! Looking forward to more videos
It was Awsome!
Tahnk you.
It might be out of context, but you have the the voice of OmniMan
lmao fr
Please make more videos on different algorithms.
Do I understand that correct, that one always needs to define a reward function (in this case score) for this type of problem?
yes
(Reward function = score function = fitness function)
Basicly all the same, and they are just to tell the algorithm if it was a bad neural network, or a good little neurie :)
This is a superb demo David. Are you able to share your github code? Thanks for the video!
I love this algorithm
"more of a lucky coincidence than a well thought out strategy"
Or as it's called when Space-X boosters use this exact strategy intentionally in real life, a "suicide burn".
sounds quite unusual of NEAT to take this long for a simple problem
Great video though!
Thats neat
why u not become the famous how
Bless you in Jesus name
????