57544b1ff9f97d4da9f64d25c8ea5a3d8d247ffc,rllib/contrib/bandits/examples/simple_context_bandit.py,,,#,38

Before Change

if __name__ == "__main__":
    args = parser.parse_args()
    tune.run(
        args.run,
        stop={
            "episode_reward_mean": args.stop_at_reward,
        },
        config={
            "env": SimpleContextualBandit,
        })

After Change

if __name__ == "__main__":
    args = parser.parse_args()

    stop = {
        "training_iteration": args.stop_iters,
        "timesteps_total": args.stop_timesteps,
        "episode_reward_mean": args.stop_reward,
    }

    config = {
        "env": SimpleContextualBandit,
    }

    results = tune.run(args.run, config=config, stop=stop)

    if args.as_test:
        check_learning_achieved(results, args.stop_reward)

Instances