mtrazzi / meta_rl Goto Github PK

 for _ in range(1):
      # to optimize for GPU, update on large batches of episodes
      d = False
      r = 0
      a = 0
      t = 0
      s = self.env.reset()
      # Allow us to remove noise when starting episode
      for i in range(5):
        _, r_, _, _ = self.env.step(np.array([0, 0, 0, 0, 0, 0, 0], dtype=np.intc))

      start_time = time.time()
      while d == False:
        #Take an action using probabilities from policy network output.
        a_dist,v,rnn_state_new = sess.run([self.local_AC.policy,self.local_AC.value,self.local_AC.state_out],
          feed_dict={
          self.local_AC.state:[s],
          self.local_AC.prev_rewards:[[r]],
          self.local_AC.timestep:[[t]],
          self.local_AC.prev_actions:[a],
          self.local_AC.state_in[0]:rnn_state[0],
          self.local_AC.state_in[1]:rnn_state[1]})

        a = np.random.choice(a_dist[0],p=a_dist[0])
        a = np.argmax(a_dist == a)
        rnn_state = rnn_state_new
        action = deepmind_action_api(a)

        """Objectif: Reduce action space to speed up training time

        1st Action: No-Op, wait 1 frame to allow pictures to appears
        2nd Action: True Action taken
        3rd Action: Reverse action to go back at the center of the screen
        4th Action: No-Op, to wait 1 frame to allow the cross to appears
        """
        _, r_, _, _ = self.env.step(np.array([0, 0, 0, 0, 0, 0, 0], dtype=np.intc))
        s1, r, d, t = self.env.step(action, True)
        r += r_
        if not d:
            _, r_, d, _ = self.env.step(-action)
            r += r_
            if not d:
                _, r_, d, _ = self.env.step(np.array([0, 0, 0, 0, 0, 0, 0], dtype=np.intc))
                r += r_

        episode_buffer.append([s,a,r,t,d,v[0,0]])
        episode_values.append(v[0,0])
        episode_reward += r
        total_steps += 1
        episode_step_count += 1
        s = s1