hula.DeepR.FeedForwardLayer
hula/DeepR.py
import hula.DeepR.FeedForwardLayer
from hula.DeepR import FeedForwardLayer
FeedForwardLayer( inputs, outputs, activation_func )
Generated nodes with the activation function activation_func
with the size of inputs
byoutputs
FeedForwardLayer.activate( X )
Feeds X
through it's nodes, and returns the output
FeedForwardLayer.randomAct( alpha )
Generates a random action to apply to its weights, then stores it for scoring later
FeedForwardLayer.score( score )
Applies score
to the stored actions
FeedForwardLayer.simplify( threshold, min_score )
Groups together states with threshold
distance from each other, then only allows states that have a score higher than min_score
to rejoin the State-Action Tree
FeedForwardLayer.train( alpha )
Applies the best selected actions according to their state's distance from the current state as well as their score, then only applies alpha
percentage of the action.
Last updated
Was this helpful?