def test_function():
with tf.Graph().as_default():
x = tf.placeholder(tf.int32, (), name="x")
y = tf.placeholder(tf.int32, (), name="y")
z = 3 * x + 2 * y
lin = function([x, y], z, givens={y: 0})
with single_threaded_session():
initialize()
assert lin(2) == 6
assert lin(2, 2) == 10
def test_multikwargs():
with tf.Graph().as_default():
x = tf.placeholder(tf.int32, (), name="x")
with tf.variable_scope("other"):
x2 = tf.placeholder(tf.int32, (), name="x")
z = 3 * x + 2 * x2
lin = function([x, x2], z, givens={x2: 0})
with single_threaded_session():
initialize()
assert lin(2) == 6
assert lin(2, 2) == 10
expt_caught = False
def test_runningmeanstd():
for (x1, x2, x3) in [
(np.random.randn(3), np.random.randn(4), np.random.randn(5)),
(np.random.randn(3, 2), np.random.randn(4, 2), np.random.randn(5, 2)),
]:
rms = RunningMeanStd(epsilon=0.0, shape=x1.shape[1:])
U.initialize()
x = np.concatenate([x1, x2, x3], axis=0)
ms1 = [x.mean(axis=0), x.std(axis=0)]
rms.update(x1)
rms.update(x2)
rms.update(x3)
ms2 = [rms.mean.eval(), rms.std.eval()]
assert np.allclose(ms1, ms2)
def test_dist():
np.random.seed(0)
p1, p2, p3 = (np.random.randn(3, 1), np.random.randn(4, 1),
np.random.randn(5, 1))
q1, q2, q3 = (np.random.randn(6, 1), np.random.randn(7, 1),
np.random.randn(8, 1))
# p1,p2,p3=(np.random.randn(3), np.random.randn(4), np.random.randn(5))
# q1,q2,q3=(np.random.randn(6), np.random.randn(7), np.random.randn(8))
comm = MPI.COMM_WORLD
assert comm.Get_size() == 2
if comm.Get_rank() == 0:
x1, x2, x3 = p1, p2, p3
elif comm.Get_rank() == 1:
x1, x2, x3 = q1, q2, q3
else:
assert False
rms = RunningMeanStd(epsilon=0.0, shape=(1, ))
U.initialize()
rms.update(x1)
rms.update(x2)
rms.update(x3)
bigvec = np.concatenate([p1, p2, p3, q1, q2, q3])
def checkallclose(x, y):
print(x, y)
return np.allclose(x, y)
assert checkallclose(
bigvec.mean(axis=0),
rms.mean.eval(),
)
assert checkallclose(
bigvec.std(axis=0),
rms.std.eval(),
)
def __init__(self, ob_dim, ac_dim): #pylint: disable=W0613
X = tf.placeholder(tf.float32, shape=[None, ob_dim*2+ac_dim*2+2]) # batch of observations
vtarg_n = tf.placeholder(tf.float32, shape=[None], name='vtarg')
wd_dict = {}
h1 = tf.nn.elu(dense(X, 64, "h1", weight_init=U.normc_initializer(1.0), bias_init=0, weight_loss_dict=wd_dict))
h2 = tf.nn.elu(dense(h1, 64, "h2", weight_init=U.normc_initializer(1.0), bias_init=0, weight_loss_dict=wd_dict))
vpred_n = dense(h2, 1, "hfinal", weight_init=U.normc_initializer(1.0), bias_init=0, weight_loss_dict=wd_dict)[:,0]
sample_vpred_n = vpred_n + tf.random_normal(tf.shape(vpred_n))
wd_loss = tf.get_collection("vf_losses", None)
loss = tf.reduce_mean(tf.square(vpred_n - vtarg_n)) + tf.add_n(wd_loss)
loss_sampled = tf.reduce_mean(tf.square(vpred_n - tf.stop_gradient(sample_vpred_n)))
self._predict = U.function([X], vpred_n)
optim = kfac.KfacOptimizer(learning_rate=0.001, cold_lr=0.001*(1-0.9), momentum=0.9, \
clip_kl=0.3, epsilon=0.1, stats_decay=0.95, \
async=1, kfac_update=2, cold_iter=50, \
weight_decay_dict=wd_dict, max_grad_norm=None)
vf_var_list = []
for var in tf.trainable_variables():
if "vf" in var.name:
vf_var_list.append(var)
update_op, self.q_runner = optim.minimize(loss, loss_sampled, var_list=vf_var_list)
self.do_update = U.function([X, vtarg_n], update_op) #pylint: disable=E1101
U.initialize() # Initialize uninitialized TF variables
def __init__(self, ob_dim, ac_dim):
# Here we'll construct a bunch of expressions, which will be used in two places:
# (1) When sampling actions
# (2) When computing loss functions, for the policy update
# Variables specific to (1) have the word "sampled" in them,
# whereas variables specific to (2) have the word "old" in them
ob_no = tf.placeholder(tf.float32, shape=[None, ob_dim * 2],
name="ob") # batch of observations
oldac_na = tf.placeholder(
tf.float32, shape=[None, ac_dim],
name="ac") # batch of actions previous actions
oldac_dist = tf.placeholder(
tf.float32, shape=[None, ac_dim * 2], name="oldac_dist"
) # batch of actions previous action distributions
adv_n = tf.placeholder(tf.float32, shape=[None],
name="adv") # advantage function estimate
wd_dict = {}
h1 = tf.nn.tanh(
dense(ob_no,
64,
"h1",
weight_init=U.normc_initializer(1.0),
bias_init=0.0,
weight_loss_dict=wd_dict))
h2 = tf.nn.tanh(
dense(h1,
64,
"h2",
weight_init=U.normc_initializer(1.0),
bias_init=0.0,
weight_loss_dict=wd_dict))
mean_na = dense(h2,
ac_dim,
"mean",
weight_init=U.normc_initializer(0.1),
bias_init=0.0,
weight_loss_dict=wd_dict) # Mean control output
self.wd_dict = wd_dict
self.logstd_1a = logstd_1a = tf.get_variable(
"logstd", [ac_dim], tf.float32,
tf.zeros_initializer()) # Variance on outputs
logstd_1a = tf.expand_dims(logstd_1a, 0)
std_1a = tf.exp(logstd_1a)
std_na = tf.tile(std_1a, [tf.shape(mean_na)[0], 1])
ac_dist = tf.concat([
tf.reshape(mean_na, [-1, ac_dim]),
tf.reshape(std_na, [-1, ac_dim])
], 1)
sampled_ac_na = tf.random_normal(
tf.shape(ac_dist[:, ac_dim:])
) * ac_dist[:,
ac_dim:] + ac_dist[:, :
ac_dim] # This is the sampled action we'll perform.
logprobsampled_n = -tf.reduce_sum(tf.log(
ac_dist[:, ac_dim:]), axis=1) - 0.5 * tf.log(
2.0 * np.pi) * ac_dim - 0.5 * tf.reduce_sum(
tf.square(ac_dist[:, :ac_dim] - sampled_ac_na) /
(tf.square(ac_dist[:, ac_dim:])),
axis=1) # Logprob of sampled action
logprob_n = -tf.reduce_sum(
tf.log(ac_dist[:, ac_dim:]), axis=1
) - 0.5 * tf.log(2.0 * np.pi) * ac_dim - 0.5 * tf.reduce_sum(
tf.square(ac_dist[:, :ac_dim] - oldac_na) /
(tf.square(ac_dist[:, ac_dim:])),
axis=1
) # Logprob of previous actions under CURRENT policy (whereas oldlogprob_n is under OLD policy)
kl = tf.reduce_mean(kl_div(oldac_dist, ac_dist, ac_dim))
#kl = .5 * tf.reduce_mean(tf.square(logprob_n - oldlogprob_n)) # Approximation of KL divergence between old policy used to generate actions, and new policy used to compute logprob_n
surr = -tf.reduce_mean(
adv_n * logprob_n
) # Loss function that we'll differentiate to get the policy gradient
surr_sampled = -tf.reduce_mean(logprob_n) # Sampled loss of the policy
self._act = U.function([ob_no],
[sampled_ac_na, ac_dist, logprobsampled_n
]) # Generate a new action and its logprob
#self.compute_kl = U.function([ob_no, oldac_na, oldlogprob_n], kl) # Compute (approximate) KL divergence between old policy and new policy
self.compute_kl = U.function([ob_no, oldac_dist], kl)
self.update_info = (
(ob_no, oldac_na, adv_n), surr, surr_sampled
) # Input and output variables needed for computing loss
U.initialize() # Initialize uninitialized TF variables
def learn(env,
policy,
vf,
gamma,
lam,
timesteps_per_batch,
num_timesteps,
animate=False,
callback=None,
desired_kl=0.002):
obfilter = ZFilter(env.observation_space.shape)
max_pathlength = env.spec.timestep_limit
stepsize = tf.Variable(initial_value=np.float32(np.array(0.03)),
name='stepsize')
inputs, loss, loss_sampled = policy.update_info
optim = kfac.KfacOptimizer(learning_rate=stepsize, cold_lr=stepsize*(1-0.9), momentum=0.9, kfac_update=2,\
epsilon=1e-2, stats_decay=0.99, async=1, cold_iter=1,
weight_decay_dict=policy.wd_dict, max_grad_norm=None)
pi_var_list = []
for var in tf.trainable_variables():
if "pi" in var.name:
pi_var_list.append(var)
update_op, q_runner = optim.minimize(loss,
loss_sampled,
var_list=pi_var_list)
do_update = U.function(inputs, update_op)
U.initialize()
# start queue runners
enqueue_threads = []
coord = tf.train.Coordinator()
for qr in [q_runner, vf.q_runner]:
assert (qr != None)
enqueue_threads.extend(
qr.create_threads(tf.get_default_session(),
coord=coord,
start=True))
i = 0
timesteps_so_far = 0
while True:
if timesteps_so_far > num_timesteps:
break
logger.log("********** Iteration %i ************" % i)
# Collect paths until we have enough timesteps
timesteps_this_batch = 0
paths = []
while True:
path = rollout(env,
policy,
max_pathlength,
animate=(len(paths) == 0 and (i % 10 == 0)
and animate),
obfilter=obfilter)
paths.append(path)
n = pathlength(path)
timesteps_this_batch += n
timesteps_so_far += n
if timesteps_this_batch > timesteps_per_batch:
break
# Estimate advantage function
vtargs = []
advs = []
for path in paths:
rew_t = path["reward"]
return_t = common.discount(rew_t, gamma)
vtargs.append(return_t)
vpred_t = vf.predict(path)
vpred_t = np.append(vpred_t,
0.0 if path["terminated"] else vpred_t[-1])
delta_t = rew_t + gamma * vpred_t[1:] - vpred_t[:-1]
adv_t = common.discount(delta_t, gamma * lam)
advs.append(adv_t)
# Update value function
vf.fit(paths, vtargs)
# Build arrays for policy update
ob_no = np.concatenate([path["observation"] for path in paths])
action_na = np.concatenate([path["action"] for path in paths])
oldac_dist = np.concatenate([path["action_dist"] for path in paths])
adv_n = np.concatenate(advs)
standardized_adv_n = (adv_n - adv_n.mean()) / (adv_n.std() + 1e-8)
# Policy update
do_update(ob_no, action_na, standardized_adv_n)
min_stepsize = np.float32(1e-8)
max_stepsize = np.float32(1e0)
# Adjust stepsize
kl = policy.compute_kl(ob_no, oldac_dist)
if kl > desired_kl * 2:
logger.log("kl too high")
tf.assign(stepsize, tf.maximum(min_stepsize,
stepsize / 1.5)).eval()
elif kl < desired_kl / 2:
logger.log("kl too low")
tf.assign(stepsize, tf.minimum(max_stepsize,
stepsize * 1.5)).eval()
else:
logger.log("kl just right!")
logger.record_tabular(
"EpRewMean", np.mean([path["reward"].sum() for path in paths]))
logger.record_tabular(
"EpRewSEM",
np.std([
path["reward"].sum() / np.sqrt(len(paths)) for path in paths
]))
logger.record_tabular("EpLenMean",
np.mean([pathlength(path) for path in paths]))
logger.record_tabular("KL", kl)
if callback:
callback()
logger.dump_tabular()
i += 1
coord.request_stop()
coord.join(enqueue_threads)