817ebfc8f001bb9a04920e84ab937897eafb1c99,a2c/a2c.py,,learn,#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#,833

Before Change

  //enqueue_threads = model.q_runner.create_threads(model.sess, coord=tf.train.Coordinator(), start=True)
  for update in range(1, total_timesteps//nbatch+1):
    obs, states, rewards, masks, actions, sub3, sub4, sub5, sub6, sub7, sub8, sub9, sub10, sub11, sub12, x0, y0, x1, y1, x2, y2, values = runner.run()
    policy_loss, value_loss, policy_entropy, \
    policy_loss_sub3, policy_entropy_sub3, \
    policy_loss_sub4, policy_entropy_sub4, \
    policy_loss_sub5, policy_entropy_sub5, \

After Change

      logger.record_tabular("policy_loss_x0", float(policy_loss_x0))
      logger.record_tabular("policy_entropy_x0", float(policy_entropy_x0))
      logger.record_tabular("policy_loss_y0", float(policy_loss_y0))
      logger.record_tabular("policy_entropy_y0", float(policy_entropy_y0))

      logger.record_tabular("value_loss", float(value_loss))
      logger.record_tabular("explained_variance", float(ev))
      logger.dump_tabular()

Instances