def __init_

def init()

in baselines/ppo2/model.py [0:0]
58 lines of code
10 McCabe index (conditional complexity)

    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
def __init__()

def init()
