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
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(x=3) == 9 assert lin(2, 2) == 10 assert lin(x=2, y=3) == 12
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, *, policy, ob_space, ac_space, nbatch_act, nbatch_train, nsteps, ent_coef, vf_coef, max_grad_norm, mpi_rank_weight=1, comm=None, microbatch_size=None): self.sess = sess = get_session() if MPI is not None and comm is None: comm = MPI.COMM_WORLD with tf.variable_scope('ppo2_model', reuse=tf.AUTO_REUSE): # CREATE OUR TWO MODELS # act_model that is used for sampling act_model = policy(nbatch_act, 1, sess) # Train model for training if microbatch_size is None: train_model = policy(nbatch_train, nsteps, sess) else: train_model = policy(microbatch_size, nsteps, sess) # CREATE THE PLACEHOLDERS self.A = A = train_model.pdtype.sample_placeholder([None]) self.ADV = ADV = tf.placeholder(tf.float32, [None]) self.R = R = tf.placeholder(tf.float32, [None]) # Keep track of old actor self.OLDNEGLOGPAC = OLDNEGLOGPAC = tf.placeholder(tf.float32, [None]) # Keep track of old critic self.OLDVPRED = OLDVPRED = tf.placeholder(tf.float32, [None]) self.LR = LR = tf.placeholder(tf.float32, []) # Cliprange self.CLIPRANGE = CLIPRANGE = tf.placeholder(tf.float32, []) neglogpac = train_model.pd.neglogp(A) # Calculate the entropy # Entropy is used to improve exploration by limiting the premature convergence to suboptimal policy. entropy = tf.reduce_mean(train_model.pd.entropy()) # CALCULATE THE LOSS # Total loss = Policy gradient loss - entropy * entropy coefficient + Value coefficient * value loss # Clip the value to reduce variability during Critic training # Get the predicted value vpred = train_model.vf vpredclipped = OLDVPRED + tf.clip_by_value(train_model.vf - OLDVPRED, - CLIPRANGE, CLIPRANGE) # Unclipped value vf_losses1 = tf.square(vpred - R) # Clipped value vf_losses2 = tf.square(vpredclipped - R) vf_loss = .5 * tf.reduce_mean(tf.maximum(vf_losses1, vf_losses2)) # Calculate ratio (pi current policy / pi old policy) ratio = tf.exp(OLDNEGLOGPAC - neglogpac) # Defining Loss = - J is equivalent to max J pg_losses = -ADV * ratio pg_losses2 = -ADV * tf.clip_by_value(ratio, 1.0 - CLIPRANGE, 1.0 + CLIPRANGE) # Final PG loss pg_loss = tf.reduce_mean(tf.maximum(pg_losses, pg_losses2)) approxkl = .5 * tf.reduce_mean(tf.square(neglogpac - OLDNEGLOGPAC)) clipfrac = tf.reduce_mean(tf.to_float(tf.greater(tf.abs(ratio - 1.0), CLIPRANGE))) # Total loss loss = pg_loss - entropy * ent_coef + vf_loss * vf_coef # UPDATE THE PARAMETERS USING LOSS # 1. Get the model parameters params = tf.trainable_variables('ppo2_model') # 2. Build our trainer if comm is not None and comm.Get_size() > 1: self.trainer = MpiAdamOptimizer(comm, learning_rate=LR, mpi_rank_weight=mpi_rank_weight, epsilon=1e-5) else: self.trainer = tf.train.AdamOptimizer(learning_rate=LR, epsilon=1e-5) # 3. Calculate the gradients grads_and_var = self.trainer.compute_gradients(loss, params) grads, var = zip(*grads_and_var) if max_grad_norm is not None: # Clip the gradients (normalize) grads, _grad_norm = tf.clip_by_global_norm(grads, max_grad_norm) grads_and_var = list(zip(grads, var)) # zip aggregate each gradient with parameters associated # For instance zip(ABCD, xyza) => Ax, By, Cz, Da self.grads = grads self.var = var self._train_op = self.trainer.apply_gradients(grads_and_var) self.loss_names = ['policy_loss', 'value_loss', 'policy_entropy', 'approxkl', 'clipfrac'] self.stats_list = [pg_loss, vf_loss, entropy, approxkl, clipfrac] self.train_model = train_model self.act_model = act_model self.step = act_model.step self.value = act_model.value self.initial_state = act_model.initial_state self.save = functools.partial(save_variables, sess=sess) self.load = functools.partial(load_variables, sess=sess) initialize() global_variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="") if MPI is not None: sync_from_root(sess, global_variables, comm=comm) #pylint: disable=E1101