def update_pi()

in safe_rl/pg/agents.py [0:0]

• 11 lines of code
• 3 McCabe index (conditional complexity)

    def update_pi(self, inputs):

        # Things we need from training package
        train_pi = self.training_package['train_pi']
        d_kl = self.training_package['d_kl']
        target_kl = self.training_package['target_kl']

        # Run the update
        for i in range(self.pi_iters):
            _, kl = self.sess.run([train_pi, d_kl], feed_dict=inputs)
            kl = mpi_avg(kl)
            if kl > self.kl_margin * target_kl:
                self.logger.log('Early stopping at step %d due to reaching max kl.'%i)
                break
        self.logger.store(StopIter=i)