garlicdevs / fruit-api Goto Github PK

i have an issue with matplotlib, i couldnt disable Disable Show plots in toolwindow because i coumdt find Python Scientific, is there anything else to do to fix this?
im using community version

hello, wanted to ask u if possible, why did u choose this number of input and output in the layers?
layer_1 = self.layer_manager.create_conv_layer(self.tf_inputs_norm, 32, 8, strides=4, activation_fn='relu',
padding='valid', scope='tf_layer_1')
layer_2 = self.layer_manager.create_conv_layer(layer_1, 64, 4, strides=2, activation_fn='relu', padding='valid',
scope='tf_layer_2')
layer_3 = self.layer_manager.create_conv_layer(layer_2, 64, 3, strides=1, activation_fn='relu', padding='valid',
scope='tf_layer_3')
layer_4 = self.layer_manager.create_fully_connected_layer(layer_3, 512, activation_fn='relu',
scope='tf_layer_4')
as i know the number of outputs in the output layer should be the number of possible actions in the environment, and the input is the state

how to get the pareto front after training a model, saving it and evaluating?

i would like to know please, what is reward_clip_thresholds? and why it is set to None in MODQNLearner(DQNLearner)?
also do u have the algorithm to share with us of the MODQNLearner, so we can understand it better, cause in ur code their is no comments which makes it harder to guess how it works, thanks in advance

there is always this error occurring altho i did all the steps correctly

i have a number of actions that varies and get less with each step, does the MODQNLearner takes this in consideration and randoms from the possible actions left in each step?

in my engine i'm using this function to calculate action space
def get_action_space(self):
return range(len(self.get_possible_actions()))

each time it gets less, so if the MODQNLearner calls it each time it performs an action, i guess it takes it in consideration