9244bd5001c2a3f8146bd7e14784c69fdbfe2d66,gym/scoreboard/tests/test_scoring.py,,test_total_reward_benchmark_extra,#,352

Before Change

    benchmark_results = defaultdict(list)
    for i, task in enumerate(reward_benchmark.tasks):
        env_id = task.env_id
        benchmark_results[env_id].append(reward_benchmark.score_evaluation(
            env_id,
            data_sources=[0],
            initial_reset_timestamps=[1],
            episode_lengths=[1],
            episode_rewards=[1],
            episode_types=["t"],
            timestamps=[i + 2],
        ))

    // add one more at the end with a high reward
    benchmark_results[env_id].append(reward_benchmark.score_evaluation(

After Change

    benchmark_results = defaultdict(list)
    for i, task in enumerate(reward_benchmark.tasks):
        env_id = task.env_id
        benchmark_results[env_id].append(_benchmark_result_helper(reward_benchmark, env_id=env_id, timestamps=[i + 2]))

    // add one more at the end with a high reward
    benchmark_results[env_id].append(_benchmark_result_helper(reward_benchmark, env_id=env_id, episode_rewards=[100], timestamps=[2]))

Instances