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

Before Change

    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)

After Change

            break


if __name__ == "__main__":
    main()

Instances