reinforcement_learning/actor_critic.py [161:184]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            ep_reward += reward
            if done:
                break

        # update cumulative reward
        running_reward = 0.05 * ep_reward + (1 - 0.05) * running_reward

        # perform backprop
        finish_episode()

        # log results
        if i_episode % args.log_interval == 0:
            print('Episode {}\tLast reward: {:.2f}\tAverage reward: {:.2f}'.format(
                  i_episode, ep_reward, running_reward))

        # check if we have "solved" the cart pole problem
        if running_reward > env.spec.reward_threshold:
            print("Solved! Running reward is now {} and "
                  "the last episode runs to {} time steps!".format(running_reward, t))
            break


if __name__ == '__main__':
    main()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



reinforcement_learning/reinforce.py [91:107]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            ep_reward += reward
            if done:
                break

        running_reward = 0.05 * ep_reward + (1 - 0.05) * running_reward
        finish_episode()
        if i_episode % args.log_interval == 0:
            print('Episode {}\tLast reward: {:.2f}\tAverage reward: {:.2f}'.format(
                  i_episode, ep_reward, running_reward))
        if running_reward > env.spec.reward_threshold:
            print("Solved! Running reward is now {} and "
                  "the last episode runs to {} time steps!".format(running_reward, t))
            break


if __name__ == '__main__':
    main()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -