To be honest, the code itself is not very complex, is only few hundreds lines of code. I pretty much followed the Cokemons path, there is plenty of amazing tutorials on this matter, I started with channel called "the coding train"
I find it highly intriguing that it seems to be Right predominant, and I can't help but wonder "If it were to be given virtual hands would it be right handed?" Which sparks a thought - the first part of the track had higher error potential on the left side than it did on the right, so the neural net had to "focus" on the challenge of the left hand side, and the ease of the right; perhaps _this_ contributed to it's right dominance.
I agree with Pablo Pazos, that would be cool if you could give an overview of what is really happening to the neural network algorithm during a test, and what are the changes for each generation
This is not a NEAT implementation, so the network structure doesn't evolve, just the weights. After each population is done I use generic algorithm to generate a new population, I use ranking based selection combined with stochastic universal sampling to select mating pool. Than new gene will have weights from either parent A or B, I have tried to crossover entire layers but this didn't give me good results. Than each weights has a chance to mutate meaning it will get new random value withing the weights range.
oh yeah i could see in the video that the network structure doesn't evolve. Actually i had a question about the hidden nodes : how did you choose the number of those "hidden" nodes ? Does it depend on something or have you just choose a number without any clear reason ? This is very interesting anyway, and the way your NN masters the track at generation 33 is very impressive. Thank you for your explaination.
Well from what I learned the number of hidden nodes is arbitrary chosen, that's why NEAT is much better because skips the limitations of this prerequisite. I also learned somewhere that in general is good to have at least inputs+1.
I don't have the slightest clue as to how they works or programmed. But this fascinates me beyond belief :D Remember watching something with Super mario 3 some years back, about neural net learning to play.
I did something very similar (without the cool graphics) using TD(lambda) in 1998 with the goal of fastest laps using a reward function of "-1" each second and something really severe (-100?) for crashing. It worked pretty well, though occasionally I'd grow a pathological variation that would minimize the function by crashing as soon as it was able. This is really cool stuff. Thanks for sharing.
very nice, how did you go about using a genetic algorithm? based off one of your previous comments I see that you only passed the weights, meaning an offspring got 100% weights from A or B? What about your biases? Were these static or initialized with every new vehicle! Thanks for sharing your research! :D
The offspring is created through a "crossover - nodes", so each neuron will get all incoming weights from (random) one of the parents. In my implementation bias is an additional node in the previous layer and their weights are subjected to crossover and mutation similarly to any other weight. Bias value is constant though.
Ah, yes! I hypothesized that your method would be an optimal way to train a Reinforcement Learned Neural Net, although I have yet to train my first one yet. Have you compared the convergence of this method with other genetic methods? Say every parameter is a gene instead of nodes? (Sorry to probe you, I am trying to get as much data from you before I write one xD) ALSO WHAT'S THE FUNCTION TO DRAW LINES IN UNITY? ( via your NN visual in the top right corner )
Hi Jabrils, what do you think about an hybrid approach, i mean, a combination of genetic algorithm and other evolutionary strategies such as particle swarm or gravitational search algorithm...? (sorry for my english)
One suggestion for a fitness function that would take into account speed (ie. reward faster runs, punish slower runs) is to have a constant living penalty. Each time interval (eg. second), the fitness score decreases by a certain amount. This means that for faster cars, the fitness increases at a greater rate. However you would either want to do this once the cars can sorta get around the track or have it be non-linear. Otherwise they'd learn too slowly
whitepen I will test this and let you know for sure. But in theory it doesn't perceive the track itself it only reacts to sensor input, so my guess is that it should do just fine on any track with exception of ones having sharper curves than the on on learning session. In that case car maybe wouldn't know that it has to de decelerate. I will let you know when I test it.
Most of these neural networks do not consider past actions at all, so it is not a matter of memorization, however, it is possible that the decision making improperly optimized due to coincidental order of operations. In other words, certain combinations of turns may expose flawed neural connections. Also, overtraining a neural network in a sterile test environment could cause the network to completely fail to adapt to changes when brought to a less sterile environment.
I was about to ask the same thing as @whitepen. I think that a little overfitting may be produced due to imperceptible patterns in the track that it is being used for training. Would it be better if a set of tracks is used for training, let's say 5 tracks, each with different degrees in the turns or even in the width of the track? Also, is it this code available in GitHub? I'll be glad if it is.
So I tested it adding two new tracks. I paused the best genome which beaten the #1 track and switched the track. The simple track (#2) with soft turns was beaten without problem, and another track(#3) with sharp turns couldn't be beaten. So I continued to run the genetic algorithm, and the car was able to beat the #3 track after 10 more generations. Than I swap again to track #1 and it failed to beat it. Needed another 6 generations to finish it.
Very fancy demonstration. I personally started looking into Neural Networks and I was wondering if you have your code open sourced; I'd be interested in attempting a NEAT-based implementation for personal use :)
если провести еще больше лучей входных сигналов то повороты машина будет проходить плавнее. Лучи должны уходить более дальше в дорогу. А так же желательно добавить лучи по бокам.
I think it will be more accurate to use other form of crossover such as the blended crossover, because a neural network is defined on a continus domain and not a discrete domain, but in your case, it's a discrete domain in the sens that you are using the node as single point of your multi-dimension vector...!
I did something similar and came across NEAT neural networks. These work in much the same way. The problem you will have though is that your evolution becomes part of your overall algorithm. The evolution may end up causing your networks to be overtrained. They might not be able to generalise. When you bring pedestrians into the mix you might get problems as people are unpredictable.
very cool video. I'd love to hear an explanation of what's going on in that top right neural network map as it's happening... I couldn't quite figure out what that changing normal map actually meant
Always wondered if fluid dynamics could be used for more natural AI pathing, if you watch the way people walk around things it's similar to the fastest part of water flowing through rocks. The water in contact with the rock creates like a barrier type thing that makes all proceeding water flow more efficiently and naturally.
You might get better results if you added two more 'whiskers' that are extend 3-4 car lengths ahead, and are even with the left and right of the car. The two sideways whiskers you already have don't really give it much of a chance to do longer-but-smoother turns, and gives the neural network a better chance to 'know' the angle of a curve - which it currently can't, not without becoming a recurrent neural network. I'd be curious to see how it'd act if you added virtual barriers that it can see, but pass through - like lane markers. See if it picks up bad habits, like cutting corners, or drifting into other lanes.
Widzę że użyłeś random funkcji do generowania przypadkowych wewnętrznych nodów. Ja myślę nad swoimi jak zaimplementować nody w miejscach gdzie są najbardziej potrzebne i jak dowiedzieć się w którym miejscu nowy nod powinien być dodany. W ten sposób IA powinien uczyć się znacznie szybciej, niż używać przypadkowych miejsc i sprawdzać czy dodany nod poprawił funkcjonalność całej sieci neuronowej, czy odwrotnie, i kiedy rozerwać połączenia między nodami, jeśli wynik na następnym nodzie przechodzącym przez wagę ma małą wartość.
I can see the future going backwards from here. Remove human brains from driving, replace with perfected driving matrix, create a robot neural network and slowly introduce brains back into driving. It will be kind of like the Server / Client of the 70's moving to the personal computer of the 80's & 90's now moving back to the Server (Cloud) / Client (Device) model.
I think it could perform better if it were Recurrent Neural Network (e.g. LSTM, GRU, or plain RNN) since it knows what it was doing. For example, it could accelerate more if it has been driving straight for a long time.
are those sensors boolean sensors? what if you extend them and feed in the 3 distance vectors instead (9 ANN inputs vs 3), that way it can speed up on straightaways and slow down around curves
Really nice. Like you I also started with coding train. I’m probably going to create basic bit based chromosome and train against a fitting function. I’m impressed how to use neural networks in the place of chromosomes. I guess you already made them fully connected and used this genetic algorithm for the weights only training only.
Hi! I am doing a very similar project in UE4. What kind of mutation did you use? Also, did you use recombination? What kind? One point crossover, two point or uniform? Thanks!
Nice! Try see if PSO weight changing might perform better in terms of learning speed and at time interval. Could you put this on git? Would be fun to test some new ideas with 🤘
Is your fitness just the distance the car goes, or also using the time? If you would use the time, and make the max-speed unlimited, it would be possible to get the ai to learn to go even faster and getting more efficient, right?
Is there sensibility to turn or variable speed controlled by the neural network ? If not why did you use a hidden layer ? Just connecting the inputs to the outputs works.
Have you tried adding recurrent connections, so that the car has some sense of velocity/memory? Also, why don't give it more or longer distance sensors?
Watching the red and green lines, it appears to me that it learned that if it is able to turn right, it should veer right, or if it can go left, it should veer left, and it should only go straight if that's the only option available. Does that seem accurate?
Hey, can you tell me, what strategy did you use, when mutating the weights? Also, how many networks were discarded and replaced in each generation. Thanks.
Are all the output values only calculated according to the three vision input? It seems to me that there is no internal memory in the computation that would take record of the past. I mean, the neural network will not being able to take account of the curvature of the track, because he only knows how much he is to the left and to the right. Am I correct?
Any reason to use genetic programming instead of gradient descent for this? Gradient descent is more efficient as it will change weights in the "right direction" instead of doing it randomly.
Tomek S isn't it also because GD requires the knowledge of the right output for every training sample? As far as I understand the correct output is unknown in this scenario
GD requires just the (differentiable) objective function; nothing else. It's only such that in supervised learning settings, we need ground-truths to evaluate our objective function. Otherwise, GD doesn't put any restrictions on availability of ground-truths. If you are faced with a problem setting where you can compute utility/objective function even without ground-truths (such as this one), GD will perform just as fine, I think.
Truly Awesome. Can you please tell me how to integrate AI into Unity and what is your GPU configuration?? Your help will be appreciated because I also want to work on a similar project.
we re trying to build a similar project, can you please explain the measure of fitness and fitness function in your implementation. we re planning to make the AI just control the steering, the acceleration will be fixed so the time elapsed seems like a good measure for fitness isnt it?
Hurdalık Cini I had distance + square root of avg velocity. Or something like this. But with constant speed just distance should do for simple project otherwise you can measure dangerous situations i.e. too close to wall etc.
Tomek S thanks for the reply, we will use distance, one more thing what about the threshold values of neurons are they constant or are they included in the chromosome and evolve with the weights?
it would be nice to see a step by step of designing this, it is very interesting!
Step 1: Forget step by step youtube tutorials.
Step 2: Google is your friend.
Step 3: Learn instead of c&p.
so where to start... :(
To be honest, the code itself is not very complex, is only few hundreds lines of code. I pretty much followed the Cokemons path, there is plenty of amazing tutorials on this matter, I started with channel called "the coding train"
Plot twist: UA-cam, in a sense, is Google
he means "Sometimes, Video is better than Texts."
Generation 1623: Déjà Vu! I've just been in this place before!
Literally
They grow so fast :(
lol
lol
lol
Lol
lol
If you change the music to Euro Beat, The car will start to drift
RaZeoniK I was looking for this comment
CRAZY Goldy Hahahahaha
Best comment
Japan
I find it highly intriguing that it seems to be Right predominant, and I can't help but wonder "If it were to be given virtual hands would it be right handed?" Which sparks a thought - the first part of the track had higher error potential on the left side than it did on the right, so the neural net had to "focus" on the challenge of the left hand side, and the ease of the right; perhaps _this_ contributed to it's right dominance.
This is actually really realistic. Looks like my first day driving
I agree with Pablo Pazos, that would be cool if you could give an overview of what is really happening to the neural network algorithm during a test, and what are the changes for each generation
This is not a NEAT implementation, so the network structure doesn't evolve, just the weights. After each population is done I use generic algorithm to generate a new population, I use ranking based selection combined with stochastic universal sampling to select mating pool. Than new gene will have weights from either parent A or B, I have tried to crossover entire layers but this didn't give me good results. Than each weights has a chance to mutate meaning it will get new random value withing the weights range.
oh yeah i could see in the video that the network structure doesn't evolve. Actually i had a question about the hidden nodes : how did you choose the number of those "hidden" nodes ? Does it depend on something or have you just choose a number without any clear reason ?
This is very interesting anyway, and the way your NN masters the track at generation 33 is very impressive.
Thank you for your explaination.
Well from what I learned the number of hidden nodes is arbitrary chosen, that's why NEAT is much better because skips the limitations of this prerequisite. I also learned somewhere that in general is good to have at least inputs+1.
+Tomek S would you be willing to post some source code?
Tomek S How would crossover work in combining two neural nets? Good work, very inspiring!
I like the use of the 3 captors,just like a line-following robot,or in this case border-avoiding.
was thinking about making GAs practical in simulations. this looks amazing
Now, add a police car and a generative adversarial network. Good job. The best I have seen so far.
I don't have the slightest clue as to how they works or programmed. But this fascinates me beyond belief :D
Remember watching something with Super mario 3 some years back, about neural net learning to play.
This is cool tomek, can you post a video of how you did this?
wrr
Zes wrrrr
more wrrr
This can be applied to the Telsa car self driving system. However, you would need a lot of crash dummies to make a finished product.
I did something very similar (without the cool graphics) using TD(lambda) in 1998 with the goal of fastest laps using a reward function of "-1" each second and something really severe (-100?) for crashing. It worked pretty well, though occasionally I'd grow a pathological variation that would minimize the function by crashing as soon as it was able.
This is really cool stuff. Thanks for sharing.
I cannot even remember what I was thinking about in 1998 probably about how angry I was that my commodore 64 didn't handle saves.
I might be off by a decade here :)
at least
Yup my 98 was all about C and assembler.
very nice, how did you go about using a genetic algorithm? based off one of your previous comments I see that you only passed the weights, meaning an offspring got 100% weights from A or B? What about your biases? Were these static or initialized with every new vehicle! Thanks for sharing your research! :D
The offspring is created through a "crossover - nodes", so each neuron will get all incoming weights from (random) one of the parents. In my implementation bias is an additional node in the previous layer and their weights are subjected to crossover and mutation similarly to any other weight. Bias value is constant though.
Ah, yes! I hypothesized that your method would be an optimal way to train a Reinforcement Learned Neural Net, although I have yet to train my first one yet. Have you compared the convergence of this method with other genetic methods? Say every parameter is a gene instead of nodes? (Sorry to probe you, I am trying to get as much data from you before I write one xD)
ALSO WHAT'S THE FUNCTION TO DRAW LINES IN UNITY? ( via your NN visual in the top right corner )
No, I didn't compare this method to any other, but I might very soon, when my NEAT solution is ready to go.
Hi Jabrils, what do you think about an hybrid approach, i mean, a combination of genetic algorithm and other evolutionary strategies such as particle swarm or gravitational search algorithm...? (sorry for my english)
@@sm4llbit sounds like a natural fit for node mutation
Still drive better than many drivers out there
One suggestion for a fitness function that would take into account speed (ie. reward faster runs, punish slower runs) is to have a constant living penalty. Each time interval (eg. second), the fitness score decreases by a certain amount. This means that for faster cars, the fitness increases at a greater rate. However you would either want to do this once the cars can sorta get around the track or have it be non-linear. Otherwise they'd learn too slowly
If you put your trained car in different tracks, will it drive without collision ? Or does it just know the track it was trained on.
whitepen I will test this and let you know for sure. But in theory it doesn't perceive the track itself it only reacts to sensor input, so my guess is that it should do just fine on any track with exception of ones having sharper curves than the on on learning session. In that case car maybe wouldn't know that it has to de decelerate. I will let you know when I test it.
Most of these neural networks do not consider past actions at all, so it is not a matter of memorization, however, it is possible that the decision making improperly optimized due to coincidental order of operations. In other words, certain combinations of turns may expose flawed neural connections.
Also, overtraining a neural network in a sterile test environment could cause the network to completely fail to adapt to changes when brought to a less sterile environment.
Amazing how that works!
I was about to ask the same thing as @whitepen. I think that a little overfitting may be produced due to imperceptible patterns in the track that it is being used for training. Would it be better if a set of tracks is used for training, let's say 5 tracks, each with different degrees in the turns or even in the width of the track?
Also, is it this code available in GitHub? I'll be glad if it is.
So I tested it adding two new tracks. I paused the best genome which beaten the #1 track and switched the track. The simple track (#2) with soft turns was beaten without problem, and another track(#3) with sharp turns couldn't be beaten. So I continued to run the genetic algorithm, and the car was able to beat the #3 track after 10 more generations. Than I swap again to track #1 and it failed to beat it. Needed another 6 generations to finish it.
Very fancy demonstration. I personally started looking into Neural Networks and I was wondering if you have your code open sourced; I'd be interested in attempting a NEAT-based implementation for personal use :)
Generation: 137, car starts to drift its way through the track
Very impressive that by gen 13 it was pretty much staying dead center most of the time.
If you had a way to construct tracks algorithmically, I think it would be fascinating to see an adversarial AI based on this.
если провести еще больше лучей входных сигналов то повороты машина будет проходить плавнее. Лучи должны уходить более дальше в дорогу. А так же желательно добавить лучи по бокам.
wow the new Cars 4 movie looks great
Still not 100% understanding neural networks but I know it' beautiful.
would be nice to see how this was done conceptually to get a sense of its applications outside of the 3D car
generation 7489: the cars made their own programming languaje and develop programs about using genetic algorithms to control cars
I think it will be more accurate to use other form of crossover such as the blended crossover, because a neural network is defined on a continus domain and not a discrete domain, but in your case, it's a discrete domain in the sens that you are using the node as single point of your multi-dimension vector...!
HI !! Nice Work !! Is the code open source ?
Hello, can you share this projet on github?
Great work.
I would like to know, how do you represent the network structure on screen. Thank you
I did something similar and came across NEAT neural networks. These work in much the same way. The problem you will have though is that your evolution becomes part of your overall algorithm. The evolution may end up causing your networks to be overtrained. They might not be able to generalise. When you bring pedestrians into the mix you might get problems as people are unpredictable.
Seems like the sensors are too short, not that it is necessarily a genetic imperfection for the sharp turning.
very cool video. I'd love to hear an explanation of what's going on in that top right neural network map as it's happening... I couldn't quite figure out what that changing normal map actually meant
Maybe if you took the same one and reversed the track it would learn to break on right turns
it's as if it doesn't remember what it just did last time. just an over all better performance by the end.
show me an ai learning a course that varies every time it tries. perhaps they'll be better at adapting into situation than we do.
Generation 70 might do some drifting.
Actual footage of me driving
That's awesome. I want to learn all about this stuff :o
They should use this to develop how cars work in gta 6, so it’s more natraul.
I'd give more length to the forward sensor. But that's just because I want THE SPEED.
Very good work! I would be interested how you are doing crossover and mutation of your networks :-)
Buying a new car in the future, it would take some time to break it in :)
DAYUM you fit, gen 14!!!
that moment you write code, but don't want to code so you code a thing hat code itself... genius
hi, Im tring to make something similar to your peoject, what activation finction did you use?
Dario Cardajoli hyperbolic tangent
Tomek S thank you very much for the answer!
Is relu suitable for this particular project?
it is interesting to see such a video.
Always wondered if fluid dynamics could be used for more natural AI pathing, if you watch the way people walk around things it's similar to the fastest part of water flowing through rocks.
The water in contact with the rock creates like a barrier type thing that makes all proceeding water flow more efficiently and naturally.
You might get better results if you added two more 'whiskers' that are extend 3-4 car lengths ahead, and are even with the left and right of the car. The two sideways whiskers you already have don't really give it much of a chance to do longer-but-smoother turns, and gives the neural network a better chance to 'know' the angle of a curve - which it currently can't, not without becoming a recurrent neural network.
I'd be curious to see how it'd act if you added virtual barriers that it can see, but pass through - like lane markers. See if it picks up bad habits, like cutting corners, or drifting into other lanes.
It would be cool if you told us what it can sense. I often wonder if these programs can only see rewards and failures
Generation 420 now the car can do *_KANSAI DORIFTO_*
Widzę że użyłeś random funkcji do generowania przypadkowych wewnętrznych nodów. Ja myślę nad swoimi jak zaimplementować nody w miejscach gdzie są najbardziej potrzebne i jak dowiedzieć się w którym miejscu nowy nod powinien być dodany.
W ten sposób IA powinien uczyć się znacznie szybciej, niż używać przypadkowych miejsc i sprawdzać czy dodany nod poprawił funkcjonalność całej sieci neuronowej, czy odwrotnie, i kiedy rozerwać połączenia między nodami, jeśli wynik na następnym nodzie przechodzącym przez wagę ma małą wartość.
I can see the future going backwards from here. Remove human brains from driving, replace with perfected driving matrix, create a robot neural network and slowly introduce brains back into driving. It will be kind of like the Server / Client of the 70's moving to the personal computer of the 80's & 90's now moving back to the Server (Cloud) / Client (Device) model.
I think it could perform better if it were Recurrent Neural Network (e.g. LSTM, GRU, or plain RNN) since it knows what it was doing. For example, it could accelerate more if it has been driving straight for a long time.
Is there any chance that you can make a tutorial series to genetic algorithms in Unity in general? I would really appreciate it
what are the inputs are the outputs? and what is the conditions of the first nodes?
Great video!!!!
Is that how self driving cars work???
interesting.. Nice Good work.
So I really want to make a project like this but I do not know where to start. Is there some video where I could learn all about this? Thanks!
is the output of the neural network just for steeri g left and right or do you also control speed?
good work bro!
are those sensors boolean sensors? what if you extend them and feed in the 3 distance vectors instead (9 ANN inputs vs 3), that way it can speed up on straightaways and slow down around curves
Would this perform better with multiple hidden layers?
Really nice. Like you I also started with coding train. I’m probably going to create basic bit based chromosome and train against a fitting function.
I’m impressed how to use neural networks in the place of chromosomes. I guess you already made them fully connected and used this genetic algorithm for the weights only training only.
Hi!
I am doing a very similar project in UE4.
What kind of mutation did you use? Also, did you use recombination? What kind? One point crossover, two point or uniform?
Thanks!
How long did this take and did you run every trial individually?
Nice! Try see if PSO weight changing might perform better in terms of learning speed and at time interval. Could you put this on git? Would be fun to test some new ideas with 🤘
Is your fitness just the distance the car goes, or also using the time?
If you would use the time, and make the max-speed unlimited, it would be possible to get the ai to learn to go even faster and getting more efficient, right?
Is there sensibility to turn or variable speed controlled by the neural network ? If not why did you use a hidden layer ? Just connecting the inputs to the outputs works.
Are you using a GA for the architecture or learning algorithm. If it's the former how do you cater for overfitting?
Have you tried adding recurrent connections, so that the car has some sense of velocity/memory?
Also, why don't give it more or longer distance sensors?
Tomek S could you post the link from where you learnt to set this up? Textbook name etc. would also help. Thanks!
Wish the video was a bit more concise and included more generations. Ergo, same length but more generations.
the inputs are the 3 sensors and the output are steer and speed?
Did it show a s shaped, learning curve?
Have you tried to learn them to avoid crashing each other?
Watching the red and green lines, it appears to me that it learned that if it is able to turn right, it should veer right, or if it can go left, it should veer left, and it should only go straight if that's the only option available. Does that seem accurate?
Hey, can you tell me, what strategy did you use, when mutating the weights? Also, how many networks were discarded and replaced in each generation. Thanks.
You need 3 sensors at rear as well for real life driving...
Show the weights of neurons, and the kind of input information. Then we can check your experience!)
You can see weight and activation as colours at right top
figures are more convenient
Are all the output values only calculated according to the three vision input? It seems to me that there is no internal memory in the computation that would take record of the past. I mean, the neural network will not being able to take account of the curvature of the track, because he only knows how much he is to the left and to the right. Am I correct?
How to make this from ground up? Any guide..?
Did you try training your network using back-propagation?
Can you please post a project so I can train my network on it?
howd you create the map?? Need help creating tracks in unity
Any reason to use genetic programming instead of gradient descent for this? Gradient descent is more efficient as it will change weights in the "right direction" instead of doing it randomly.
GD is boring ;)
Tomek S isn't it also because GD requires the knowledge of the right output for every training sample? As far as I understand the correct output is unknown in this scenario
Brain child.
GD requires just the (differentiable) objective function; nothing else. It's only such that in supervised learning settings, we need ground-truths to evaluate our objective function. Otherwise, GD doesn't put any restrictions on availability of ground-truths.
If you are faced with a problem setting where you can compute utility/objective function even without ground-truths (such as this one), GD will perform just as fine, I think.
why not using reinforcement learning? I feel in this scenario it's quite like an atari game.
why 5 hidden neurons? Could you provide the source of this project? I am interested in unity assets, not the genetic algo itself
after 9 month no source provided, great!
Any chance of Source Code being available for this project?
Great work.
Truly Awesome. Can you please tell me how to integrate AI into Unity and what is your GPU configuration?? Your help will be appreciated because I also want to work on a similar project.
Explain please why amount of genome is 10?
Is this supervised training? so the input would be the 3 sensors hit/miss? And what the outputs are? Thanks!
inputs are the distances of the sensors (not just hit/miss) output is steering and acceleration
Why do you use genetic algorithm? to update weights? why not backprop?
after the learning face is done, is it expansive possessor wise ?
What generation do you learn the left lane is for passing ?
link for the environment please
we re trying to build a similar project, can you please explain the measure of fitness and fitness function in your implementation. we re planning to make the AI just control the steering, the acceleration will be fixed so the time elapsed seems like a good measure for fitness isnt it?
Hurdalık Cini I had distance + square root of avg velocity. Or something like this. But with constant speed just distance should do for simple project otherwise you can measure dangerous situations i.e. too close to wall etc.
Tomek S thanks for the reply, we will use distance, one more thing what about the threshold values of neurons are they constant or are they included in the chromosome and evolve with the weights?
It pulled a lil drift there at the end
Could the same car in the last generation drive perfect on a new stage?
What is the type of this algorithm?Unsupervised?
how i can replicate this experiment ? You share a sourcecode?