Pownie/backgammon
1
0
Fork 0
Code Issues 6 Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'master' of gitfub.space:Pownie/backgammon

Browse Source
This commit is contained in:
Alexander Munch-Hansen 2018-03-06 12:57:38 +01:00
commit 7c9127b746
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
network.py
View File

@ -18,6 +18,11 @@ class Network:
# TODO: Actually compile tensorflow properly # TODO: Actually compile tensorflow properly
#os.environ["TF_CPP_MIN_LOG_LEVEL"]="2" #os.environ["TF_CPP_MIN_LOG_LEVEL"]="2"
def custom_tanh(self, x, name=None):
a = tf.Variable(2.00, tf.float32)
return tf.scalar_mul(a, tf.tanh(x, name))
def __init__(self, session): def __init__(self, session):
self.session = session self.session = session
@ -40,12 +45,10 @@ class Network:
b_1 = tf.zeros(hidden_size,) b_1 = tf.zeros(hidden_size,)
b_2 = tf.zeros(output_size,) b_2 = tf.zeros(output_size,)
value_after_input = tf.sigmoid(tf.matmul(self.x, W_1) + b_1, name='hidden_layer') value_after_input = self.custom_tanh(tf.matmul(self.x, W_1) + b_1, name='hidden_layer')
# TODO: Remember to make this tanh * 2 # TODO: Remember to make this tanh * 2
# self.value = tf.layers.dense(input=value_after_input, units=hidden_size, \ self.value = self.custom_tanh(tf.matmul(value_after_input, W_2) + b_2, name='output_layer')
# activation=self.custom_tanh, kernel_initializer=xavier_init())
self.value = 2*tf.nn.tanh(tf.matmul(value_after_input, W_2) + b_2, name='output_layer')
# tf.reduce_sum basically finds the sum of it's input, so this gives the difference between the two values, in case they should be lists, which they might be if our input changes # tf.reduce_sum basically finds the sum of it's input, so this gives the difference between the two values, in case they should be lists, which they might be if our input changes
difference_in_values = tf.reduce_sum(self.value_next - self.value, name='difference') difference_in_values = tf.reduce_sum(self.value_next - self.value, name='difference')
@ -67,7 +70,6 @@ class Network:
self.saver = tf.train.Saver(max_to_keep=1) self.saver = tf.train.Saver(max_to_keep=1)
self.session.run(tf.global_variables_initializer()) self.session.run(tf.global_variables_initializer())
def eval_state(self, state): def eval_state(self, state):
# Run state through a network # Run state through a network