Python baselines.common.tf_util.argmax() Examples

The following are 30 code examples of baselines.common.tf_util.argmax(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module baselines.common.tf_util , or try the search function .
Example #1
Source File: distributions.py    From HardRLWithYoutube with MIT License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #2
Source File: distributions.py    From BackpropThroughTheVoidRL with MIT License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #3
Source File: distributions.py    From lirpg with MIT License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #4
Source File: distributions.py    From MOREL with MIT License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #5
Source File: distributions.py    From deeprl-baselines with MIT License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #6
Source File: distributions.py    From DRL_DeliveryDuel with MIT License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #7
Source File: distributions.py    From sonic_contest with MIT License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #8
Source File: distributions.py    From learning2run with MIT License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=1)
Example #9
Source File: distributions.py    From self-imitation-learning with MIT License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #10
Source File: distributions.py    From rl_graph_generation with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def sample_dtype(self):
        return tf.int32

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #11
Source File: distributions.py    From ICML2019-TREX with MIT License 5 votes vote down vote up 
def pdfromlatent(self, latent_vector, init_scale=1.0, init_bias=0.0):
        pdparam = _matching_fc(latent_vector, 'pi', self.size, init_scale=init_scale, init_bias=init_bias)
        return self.pdfromflat(pdparam), pdparam

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #12
Source File: distributions.py    From ICML2019-TREX with MIT License 5 votes vote down vote up 
def pdfromlatent(self, latent_vector, init_scale=1.0, init_bias=0.0):
        pdparam = _matching_fc(latent_vector, 'pi', self.size, init_scale=init_scale, init_bias=init_bias)
        return self.pdfromflat(pdparam), pdparam

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #13
Source File: distributions.py    From ICML2019-TREX with MIT License 5 votes vote down vote up 
def mode(self):
        return tf.argmax(self.logits, axis=-1)
Example #14
Source File: distributions.py    From MOREL with MIT License 5 votes vote down vote up 
def mode(self):
        return tf.argmax(self.logits, axis=-1)
Example #15
Source File: distributions.py    From MOREL with MIT License 5 votes vote down vote up 
def sample(self):
        u = tf.random_uniform(tf.shape(self.logits))
        return tf.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #16
Source File: distributions.py    From sonic_contest with MIT License 5 votes vote down vote up 
def mode(self):
        return tf.argmax(self.logits, axis=-1)
Example #17
Source File: distributions.py    From sonic_contest with MIT License 5 votes vote down vote up 
def sample(self):
        u = tf.random_uniform(tf.shape(self.logits))
        return tf.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #18
Source File: distributions.py    From self-imitation-learning with MIT License 5 votes vote down vote up 
def mode(self):
        return tf.argmax(self.logits, axis=-1)
Example #19
Source File: distributions.py    From self-imitation-learning with MIT License 5 votes vote down vote up 
def sample(self):
        u = tf.random_uniform(tf.shape(self.logits))
        return tf.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #20
Source File: distributions.py    From baselines with MIT License 5 votes vote down vote up 
def pdfromlatent(self, latent_vector, init_scale=1.0, init_bias=0.0):
        pdparam = _matching_fc(latent_vector, 'pi', self.size, init_scale=init_scale, init_bias=init_bias)
        return self.pdfromflat(pdparam), pdparam

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #21
Source File: distributions.py    From baselines with MIT License 5 votes vote down vote up 
def mode(self):
        return tf.argmax(self.logits, axis=-1)
Example #22
Source File: distributions.py    From baselines with MIT License 5 votes vote down vote up 
def sample(self):
        u = tf.random_uniform(tf.shape(self.logits), dtype=self.logits.dtype)
        return tf.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #23
Source File: distributions.py    From deeprl-baselines with MIT License 5 votes vote down vote up 
def mode(self):
        return U.argmax(self.logits, axis=-1)
Example #24
Source File: distributions.py    From deeprl-baselines with MIT License 5 votes vote down vote up 
def sample(self):
        u = tf.random_uniform(tf.shape(self.logits))
        return tf.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #25
Source File: distributions.py    From BackpropThroughTheVoidRL with MIT License 5 votes vote down vote up 
def mode(self):
        return U.argmax(self.logits, axis=-1)
Example #26
Source File: distributions.py    From BackpropThroughTheVoidRL with MIT License 5 votes vote down vote up 
def sample(self):
        u = tf.random_uniform(tf.shape(self.logits))
        return tf.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #27
Source File: distributions.py    From Reinforcement_Learning_for_Traffic_Light_Control with Apache License 2.0 5 votes vote down vote up 
def pdfromlatent(self, latent_vector, init_scale=1.0, init_bias=0.0):
        pdparam = fc(latent_vector, 'pi', self.size, init_scale=init_scale, init_bias=init_bias)
        return self.pdfromflat(pdparam), pdparam

# WRONG SECOND DERIVATIVES
# class CategoricalPd(Pd):
#     def __init__(self, logits):
#         self.logits = logits
#         self.ps = tf.nn.softmax(logits)
#     @classmethod
#     def fromflat(cls, flat):
#         return cls(flat)
#     def flatparam(self):
#         return self.logits
#     def mode(self):
#         return U.argmax(self.logits, axis=-1)
#     def logp(self, x):
#         return -tf.nn.sparse_softmax_cross_entropy_with_logits(self.logits, x)
#     def kl(self, other):
#         return tf.nn.softmax_cross_entropy_with_logits(other.logits, self.ps) \
#                 - tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def entropy(self):
#         return tf.nn.softmax_cross_entropy_with_logits(self.logits, self.ps)
#     def sample(self):
#         u = tf.random_uniform(tf.shape(self.logits))
#         return U.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #28
Source File: distributions.py    From lirpg with MIT License 5 votes vote down vote up 
def mode(self):
        return tf.argmax(self.logits, axis=-1)
Example #29
Source File: distributions.py    From lirpg with MIT License 5 votes vote down vote up 
def sample(self):
        u = tf.random_uniform(tf.shape(self.logits))
        return tf.argmax(self.logits - tf.log(-tf.log(u)), axis=-1)
Example #30
Source File: distributions.py    From HardRLWithYoutube with MIT License 5 votes vote down vote up 
def mode(self):
        return tf.argmax(self.logits, axis=-1)