29c4c9a4f78a190deb34daa80d0d21b413d14621,Reinforcement_learning_TUT/experiments/Solve_BipedalWalker/A3C.py,Worker,work,#Worker#,119

Before Change

                        self.AC.a_his: buffer_a,
                        self.AC.v_target: buffer_v_target,
                    }
                    self.AC.update_global(feed_dict)
                    buffer_s, buffer_a, buffer_r = [], [], []
                    self.AC.pull_global()

                s = s_

After Change

                    buffer_s, buffer_a, buffer_r = [], [], []

                if total_step > MEMORY_CAPACITY and total_step % UPDATE_GLOBAL_ITER == 0:
                    sampled_batch = self.AC.sample(UPDATE_GLOBAL_ITER)
                    feed_dict = {
                        self.AC.s: sampled_batch[:, :N_S],
                        self.AC.a_his: sampled_batch[:, N_S: N_S+N_A],
                        self.AC.v_target: sampled_batch[:, -1:],
                    }
                    test = self.AC.update_global(feed_dict)
                    self.AC.pull_global()

                    if done:
                        achieve = "| Achieve" if self.env.unwrapped.hull.position[0] >= 88 else "| -------"

Instances