DataPredict [Release 1.22] - Machine Learning And Deep Learning Library (Learning AIs, Generative AIs, and more!)

Resources Community Resources
, ,
#426

You can reset it by changing the argument inside loadModelParameters() function to “nil”.


local function buildActorModel(ID)
	
	local Model = DataPredict.Models.NeuralNetwork.new(1)
	
	Model:setModelParametersInitializationMode("LeCunUniform")

	Model:addLayer(5, true, 'LeakyReLU', 0.001)

	Model:addLayer(3, true, 'LeakyReLU', 0.001)

	Model:addLayer(7, false, 'StableSoftmax', 0.001)

	Model:setClassesList({'A','D','W','S','jump','useWeapon', "none"})
	
	local ModelParameters = loadModelParameters(ActorModelDataStore, ID)
	
	Model:setModelParameters(nil) -- Here.
	
	table.insert(ActorModelArray, Model)
	
	return Model
	
end

local function buildCriticModel(ID)
	
	local Model = DataPredict.Models.NeuralNetwork.new(1)
	
	Model:setModelParametersInitializationMode("LeCunUniform")

	Model:addLayer(5, true, 'LeakyReLU', 0.001)

	Model:addLayer(3, true, 'LeakyReLU', 0.001)

	Model:addLayer(1, false, 'Sigmoid', 0.001)

	Model:setClassesList({1, 2})
	
	local ModelParameters = loadModelParameters(CriticModelDataStore, ID)
	
	Model:setModelParameters(nil) -- And here.
	
	table.insert(CriticModelArray, Model)
	
	return Model
	
end

Don’t forget to put ModelParameters back after you stop the game.

#427

btw how do u export and separate matrix value and make it an UI like this:
image

and what this do?
image

1 Like
#428

The matrices are nothing more than just a “table of table of numbers”. Anyways, since we are using a neural network model parameters, it will be a table of matrices.


for matrixNumber = 1, #ModelParameters, 1 do

	local matrix = ModelParameters[matrixNumber]
	
	for i = 1, #matrix, 1 do -- Rows
	
		for j = 1, #matrix[1], 1 do -- Columns
	
			print(matrix[i][j])
	
		end
	
	end
	
end

You might have to create your own UI though.

To answer your other question…

Model:setClassesList({1, 2})

This one is just to avoid unexpected bugs. Though, I think you can safely remove it if it bothers you that much.

#429

hey, i just let my roblox studio run while the bot training it self for a half hours and no progress result, they keep walk around like spinning.

#430

how to know which one is W, A, S, D, jump & attack?

there 7 of classes but there 6 & 4.

image
image906×661 37.5 KB

#431

Hmm, I think it is just better to use the values output from the predict() function in that case.

matrixValue = Model:predict(currentInput, true)

The columns should be the actions, and the order of the keys follow the table in setClassesList()

You can see the parameters for predict() argument here.

#432

Might need to change the Model then. I did made some changes to the code because there are so many websites giving me wrong information.

1 Like
#434

its CriticModel right? there no predict function on it.

#435

I’ll give you the full code. This is for main script:


local function onInputReceived(ID, environmentVector, rewardValue)
	
	local Model = ModelArray[ID]
	
	local ActorModel = ActorModelArray[ID]
	
	pcall(function()
		
		local output = Model:reinforce(environmentVector, rewardValue)
		
		local predictedMatrix = ActorModel:predict(environmentVector, true)
		
		MatrixL:printMatrix(predictedMatrix)
		
		OutputEvent:Fire(ID, output)

	end)

end
#436

image
image1918×328 42.7 KB

i dont know which one is the value to show on UI

#437

You can choose from a random ID. Different ID means different model parameters. So you might want to choose when ID = 1.

#438

wait, do the printed matrix is sequentially? ex:

image
image2817×120 97.9 KB

in the table there 0.000002, 0.7, 1.78e-07, and so on…, so its sequentially?

class:
A, D, W, S, jump, attack, idle → A: 0.000002, D: 1.78e-08, W: …

#439

Yep. And since we’re using softmax as our last layer, you can consider them as probabilities.

#440

image
image467×615 144 KB

finally made it.

1 Like
#441

I think its better if you format it in a way that it shows less decimal numbers… That looks like hard to read.

#442

image
image440×642 63.9 KB

4 decimal length

Reinforcement Learning Sword Fighting Version 3 (1).rbxl (214.7 KB)

edit: fixed the ui on changing model.
edit 2: fixes, add pause/resume button, better rounding decimal number (specially for negatives) & colored background when decrement/increment.

1 Like
#443

hey i have trained the bots (2 bot) for ~2 hours and they still cant fighting efficiently.

training model 1.rbxl (215.6 KB)

also learningRate

image
image1363×90 12 KB

at addLayer function, u set it as 0.001 so what if i change it to higher like 0.1 or 0.5? it will be faster or slower? also how do you create an optimizer?

#444

If you make the learning rate higher, it will make the training faster, but more likely to have a risk of “untraining” it. I prefer keeping it less than 0.5 if you really want to increase it.

For creating an optimizer, you can have a look at other optimizers that have been created. All of them inherits the BaseOptimizer class.

#445

image
image875×152 16.7 KB

do i have to increase that layer for LeakyReLU for adding more classList?

#446

Yep. The value must be equal to the length of the classesList table.