9352eece98d1205a01c2c7603538ea08a3d1f639,Reinforcement_learning_TUT/experiments/Solve_BipedalWalker/A3C.py,Worker,work,#Worker#,141

Before Change

                    buffer_v_target.reverse()

                    buffer_s, buffer_a, buffer_v_target = np.vstack(buffer_s), np.vstack(buffer_a), np.vstack(buffer_v_target)
                    buffer_t = np.hstack((buffer_s, buffer_a, buffer_v_target))
                    self.AC.store_batch_transitions(buffer_t)

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

After Change

                    if len(GLOBAL_RUNNING_R) == 0:  // record running episode reward
                        GLOBAL_RUNNING_R.append(ep_r)
                    else:
                        GLOBAL_RUNNING_R.append(0.95 * GLOBAL_RUNNING_R[-1] + 0.05 * ep_r)
                    print(
                        self.name,
                        "Ep:", GLOBAL_EP,
                        achieve,

Instances