Fix/update reinforcement learning code
Budget: €8 – €30 EUR
I have a code in reinforcement learning have 6 states ([x, y, z, x1, y1, z1]).
x1, y1, z1 are generated as random number from a range of (-1 and 1) and do not change throughout the training.
x, y, z initially are (x1, y1, z1 (+ or -) random.uniform(-0.002,0.002)).
The aim is to get x, y and z closer to x1, y1 and z1. The closeness should be atleast 10% of the very initial difference for each points, i.e abs(x-x1) < 0.1*abs(initial_x-initial_x1) and abs(y-y1) < 0.1*abs(initial_y-initial_y1) and abs(z-z1) < 0.1*abs(initial_z-initial_z1) .
I already have the code for it, but it does not work and i think the reward logic has to be update.
I want someone to check the code and fix it.
x1, y1, z1 are generated as random number from a range of (-1 and 1) and do not change throughout the training.
x, y, z initially are (x1, y1, z1 (+ or -) random.uniform(-0.002,0.002)).
The aim is to get x, y and z closer to x1, y1 and z1. The closeness should be atleast 10% of the very initial difference for each points, i.e abs(x-x1) < 0.1*abs(initial_x-initial_x1) and abs(y-y1) < 0.1*abs(initial_y-initial_y1) and abs(z-z1) < 0.1*abs(initial_z-initial_z1) .
I already have the code for it, but it does not work and i think the reward logic has to be update.
I want someone to check the code and fix it.