69f25c6028d71e23a7b267b0e1071ad216290f91,baselines/ppo2/policies.py,MlpPolicy,__init__,#MlpPolicy#Any#Any#Any#Any#Any#Any#,133

Before Change

            h1 = activ(fc(X, "vf_fc1", nh=64, init_scale=np.sqrt(2)))
            h2 = activ(fc(h1, "vf_fc2", nh=64, init_scale=np.sqrt(2)))
            vf = fc(h2, "vf", 1)[:,0]
            logstd = tf.get_variable(name="logstd", shape=[1, actdim],
                initializer=tf.zeros_initializer())

        pdparam = tf.concat([pi, pi * 0.0 + logstd], axis=1)

        self.pdtype = make_pdtype(ac_space)
        self.pd = self.pdtype.pdfromflat(pdparam)

After Change

            vf_h2 = activ(fc(vf_h1, "vf_fc2", nh=64, init_scale=np.sqrt(2)))
            vf = fc(vf_h2, "vf", 1)[:,0]

            self.pd, self.pi = self.pdtype.pdfromlatent(pi_h2, init_scale=0.01)


        a0 = self.pd.sample()

Instances