fix bugs

Author: ZYunfeii

DDPG/DDPG_spinningup/main.py

@@ -26,6 +26,13 @@
             else:
                 a = env.action_space.sample()
             o2, r, d, _ = env.step(a)
+
+            # new_goal = np.array([1.0, 0.0, 0.0], dtype=np.float32)
+            # goal_cos, goal_sin, goal_thdot = new_goal[0], new_goal[1], new_goal[2]
+            # cos_th, sin_th, thdot = o[0], o[1], o[2]
+            # costs = (goal_cos - cos_th) ** 2 + (goal_sin - sin_th) ** 2 + 0.1 * (goal_thdot - thdot) ** 2
+            # reward = 0 if costs < 0.5 else -1
+
             ddpg.replay_buffer.store(o, a, r, o2, d)
 
             if episode >= 5 and j % update_every == 0: