97e039127f068a1475988d4921169d002cca4156,baselines/ppo2/model.py,Model,__init__,#Model#,27

Before Change

        self.save = functools.partial(save_variables, sess=sess)
        self.load = functools.partial(load_variables, sess=sess)

        if MPI is None or MPI.COMM_WORLD.Get_rank() == 0:
            initialize()
        else:
            global_variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="")

After Change

        initialize()
        global_variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="")
        if MPI is not None:
            sync_from_root(sess, global_variables) //pylint: disable=E1101

    def train(self, lr, cliprange, obs, returns, masks, actions, values, neglogpacs, states=None):
        // Here we calculate advantage A(s,a) = R + yV(s") - V(s)
        // Returns = R + yV(s")
        advs = returns - values

Instances