641a28fbf0daff0ad1ad0f43d2c4b545cb6f9656,examples/reinforcement_learning/tutorial_cartpole_ac.py,Critic,learn,#Critic#Any#Any#Any#,142

Before Change

            self.train_op = tf.train.AdamOptimizer(lr).minimize(self.loss)

    def learn(self, s, r, s_):
        v_ = self.sess.run(self.v, {self.s: [s_]})
        td_error, _ = self.sess.run([self.td_error, self.train_op], {self.s: [s], self.v_: v_, self.r: r})
        return td_error


sess = tf.Session()

After Change

                // self.train_op = tf.train.AdamOptimizer(lr).minimize(self.loss)
        self.optimizer = tf.train.AdamOptimizer(lr)

    def learn(self, s, r, s_):
            // v_ = self.sess.run(self.v, {self.s: [s_]})
        v_ = self.model([s_]).outputs
            // td_error, _ = self.sess.run([self.td_error, self.train_op], {self.s: [s], self.v_: v_, self.r: r})
        with tf.GradientTape() as tape:
            v = self.model([s]).outputs
            // TD_error = r + lambd * V(newS) - V(S)
            td_error = r + LAMBDA * v_ - v
            loss = tf.square(td_error)
        grad = tape.gradient(loss, self.model.weights)
        self.optimizer.apply_gradients(zip(grad, self.model.weights))

        return td_error

Instances