New answers tagged

0

If it's a 2-player game it goes a little deeper into RL if you want both sides to be RL algorithms. I recommend reading about game theory and what is a Nash Equilibrium to start. For algorithms hiivemdptoolbox has openai-gym compatibility as well as Q-Learning. You will need to add code to make 2 learners play each other. I would also recommend adding Dyna-Q ...


0

There are many approaches - the initial one would be a rule based one with some amount of randomness. The ML-AI approach is some variation of reinforcement learning, defining your game as an environment, see for instance openai-gym. ”Some variation” might be Deep Q Learning or A3C.


1

self is used in python class methods, to denote an instance of the class in python. For example in this snippet self.name will assign the given name to the instance. class Dog: def __init__(self, name): self.name = name Here, as you're not subclassing, you should remove the self and just use model. self.model. -> model. You'll also need to ...


2

This is a pretty standard minimum "quality" (better said resolution in pixels between the eyes) needed for a facial recognition system: Ensure that the image contains a frontal view of the face, good lighting, and at least 80 pixels between the eyes. the bare minimum to identify a human face would be 25 to 75 pixels just between the eyes In the ...


2

On page 2 of Axis' web page Identification and Recognition there is an estimate of the minimum number of pixels needed for identification, recognition and detection.


Top 50 recent answers are included