ca907342507c1139696f542de0a3351d7a382eee,reinforcement_learning/reinforce.py,,,#,77

Before Change

running_reward = 10
for i_episode in count(1):
    state = env.reset()
    for t in range(10000):  // Don"t infinite loop while learning
        action = select_action(state)
        state, reward, done, _ = env.step(action)
        if args.render:
            env.render()
        policy.rewards.append(reward)
        if done:
            break

    running_reward = running_reward * 0.99 + t * 0.01
    finish_episode()
    if i_episode % args.log_interval == 0:
        print("Episode {}\tLast length: {:5d}\tAverage length: {:.2f}".format(

After Change

            break


if __name__ == "__main__":
    main()

Instances