def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False):
nbatch = nenv * nsteps
nh, nw, nc = ob_space.shape
ob_shape = (nbatch, nh, nw, nc * nstack)
nact = ac_space.n
X = tf.placeholder(tf.uint8, ob_shape) # obs
with tf.variable_scope("model", reuse=reuse):
h = nature_cnn(X)
pi_logits = fc(h, 'pi', nact, init_scale=0.01)
pi = tf.nn.softmax(pi_logits)
q = fc(h, 'q', nact)
a = sample(tf.nn.softmax(pi_logits)) # could change this to use self.pi instead
self.initial_state = [] # not stateful
self.X = X
self.pi = pi # actual policy params now
self.pi_logits = pi_logits
self.q = q
self.vf = q
def step(ob, *args, **kwargs):
# returns actions, mus, states
a0, pi0 = sess.run([a, pi], {X: ob})
return a0, pi0, [] # dummy state
def out(ob, *args, **kwargs):
pi0, q0 = sess.run([pi, q], {X: ob})
return pi0, q0
def act(ob, *args, **kwargs):
return sess.run(a, {X: ob})
self.step = step
self.out = out
self.act = act
def __init__(self, sess, ob_space, ac_space, nenv, nsteps, nstack, reuse=False, nlstm=256):
nbatch = nenv * nsteps
nh, nw, nc = ob_space.shape
ob_shape = (nbatch, nh, nw, nc * nstack)
nact = ac_space.n
X = tf.placeholder(tf.uint8, ob_shape) # obs
M = tf.placeholder(tf.float32, [nbatch]) #mask (done t-1)
S = tf.placeholder(tf.float32, [nenv, nlstm*2]) #states
with tf.variable_scope("model", reuse=reuse):
h = nature_cnn(X)
# lstm
xs = batch_to_seq(h, nenv, nsteps)
ms = batch_to_seq(M, nenv, nsteps)
h5, snew = lstm(xs, ms, S, 'lstm1', nh=nlstm)
h5 = seq_to_batch(h5)
pi_logits = fc(h5, 'pi', nact, init_scale=0.01)
pi = tf.nn.softmax(pi_logits)
q = fc(h5, 'q', nact)
a = sample(pi_logits) # could change this to use self.pi instead
self.initial_state = np.zeros((nenv, nlstm*2), dtype=np.float32)
self.X = X
self.M = M
self.S = S
self.pi = pi # actual policy params now
self.q = q
def step(ob, state, mask, *args, **kwargs):
# returns actions, mus, states
a0, pi0, s = sess.run([a, pi, snew], {X: ob, S: state, M: mask})
return a0, pi0, s
self.step = step
def __init__(self, env, observations, latent, estimate_q=False, vf_latent=None, sess=None, **tensors):
"""
Parameters:
----------
env RL environment
observations tensorflow placeholder in which the observations will be fed
latent latent state from which policy distribution parameters should be inferred
vf_latent latent state from which value function should be inferred (if None, then latent is used)
sess tensorflow session to run calculations in (if None, default session is used)
**tensors tensorflow tensors for additional attributes such as state or mask
"""
self.X = observations
self.state = tf.constant([])
self.initial_state = None
self.__dict__.update(tensors)
vf_latent = vf_latent if vf_latent is not None else latent
vf_latent = tf.layers.flatten(vf_latent)
latent = tf.layers.flatten(latent)
# Based on the action space, will select what probability distribution type
self.pdtype = make_pdtype(env.action_space)
self.pd, self.pi = self.pdtype.pdfromlatent(latent, init_scale=0.01)
# Take an action
self.action = self.pd.sample()
# Calculate the neg log of our probability
self.neglogp = self.pd.neglogp(self.action)
self.sess = sess or tf.get_default_session()
if estimate_q:
assert isinstance(env.action_space, gym.spaces.Discrete)
self.q = fc(vf_latent, 'q', env.action_space.n)
self.vf = self.q
else:
self.vf = fc(vf_latent, 'vf', 1)
self.vf = self.vf[:,0]
def network_fn(X):
h = tf.cast(X, tf.float32) / 255.
activ = tf.nn.relu
h = activ(conv(h, 'c1', nf=8, rf=8, stride=4, init_scale=np.sqrt(2), **conv_kwargs))
h = activ(conv(h, 'c2', nf=16, rf=4, stride=2, init_scale=np.sqrt(2), **conv_kwargs))
h = conv_to_fc(h)
h = activ(fc(h, 'fc1', nh=128, init_scale=np.sqrt(2)))
return h
def network_fn(X):
h = tf.layers.flatten(X)
for i in range(num_layers):
h = fc(h, 'mlp_fc{}'.format(i), nh=num_hidden, init_scale=np.sqrt(2))
if layer_norm:
h = tf.contrib.layers.layer_norm(h, center=True, scale=True)
h = activation(h)
return h
def nature_cnn(unscaled_images, **conv_kwargs):
"""
CNN from Nature paper.
"""
scaled_images = tf.cast(unscaled_images, tf.float32) / 255.
activ = tf.nn.relu
h = activ(conv(scaled_images, 'c1', nf=32, rf=8, stride=4, init_scale=np.sqrt(2),
**conv_kwargs))
h2 = activ(conv(h, 'c2', nf=64, rf=4, stride=2, init_scale=np.sqrt(2), **conv_kwargs))
h3 = activ(conv(h2, 'c3', nf=64, rf=3, stride=1, init_scale=np.sqrt(2), **conv_kwargs))
h3 = conv_to_fc(h3)
return activ(fc(h3, 'fc1', nh=512, init_scale=np.sqrt(2)))
def pdfromlatent(self, latent_vector, init_scale=1.0, init_bias=0.0):
mean = fc(latent_vector, 'pi', self.size, init_scale=init_scale, init_bias=init_bias)
logstd = tf.get_variable(name='pi/logstd', shape=[1, self.size], initializer=tf.zeros_initializer())
pdparam = tf.concat([mean, mean * 0.0 + logstd], axis=1)
return self.pdfromflat(pdparam), mean
def pdfromlatent(self, latent_vector, init_scale=1.0, init_bias=0.0):
pdparam = fc(latent_vector, 'pi', self.ncat, init_scale=init_scale, init_bias=init_bias)
return self.pdfromflat(pdparam), pdparam