PolicyNetwork Class Reference

Public Member Functions
	__init__ (self)
	setupOptim (self)
	setupTargetAssign (self, nominalNet, tau=UPDATE_RATE)

Public Attributes
	optim = optim
	policy = policy
	qgradient = qgradient
list	update_variables
	variables = tf.trainable_variables()[nvars:]
	x = x

Detailed Description

Definition at line 92 of file continuous.py.

Constructor & Destructor Documentation

__init__()

__init__

(

self

)

Definition at line 93 of file continuous.py.

Member Function Documentation

setupOptim()

setupOptim

(

self

)

Definition at line 109 of file continuous.py.

setupTargetAssign()

setupTargetAssign	(		self,
			nominalNet,
			tau = UPDATE_RATE )

Definition at line 121 of file continuous.py.

Member Data Documentation

optim

optim = optim

Definition at line 118 of file continuous.py.

policy

policy = policy

Definition at line 105 of file continuous.py.

qgradient

qgradient = qgradient

Definition at line 117 of file continuous.py.

update_variables

list update_variables

Initial value:

= [
target.assign(tau * ref + (1 - tau) * target)
for target, ref in zip(self.variables, nominalNet.variables)
]

Definition at line 122 of file continuous.py.

variables

variables = tf.trainable_variables()[nvars:]

Definition at line 107 of file continuous.py.

x

x = x

Definition at line 104 of file continuous.py.

---

The documentation for this class was generated from the following file:

• doc/d-practical-exercises/src/continuous.py