Run BREMEN on D4RL about bremen HOT 3 OPEN

import d4rl 


    def generate_d4rl_data(self, dataset_name='hopper-medium-v0', n_train=int(1e6), horizon=1000):
        print(dataset_name)
        dataset = d4rl.qlearning_dataset(gym.make(dataset_name).env)
        # datafile: str
        s1 = dataset['observations']
        s2 = dataset['next_observations']
        a1 = dataset['actions']
        r = dataset['rewards']
        data_size = max(s1.shape[0], s2.shape[0], a1.shape[0], r.shape[0])
        n_train = min(n_train, data_size)
        paths = []
        for i in range(int(n_train/horizon)):
            path = Path()
            if i*horizon % 10000 == 0:
                print(i*horizon)
            for j in range(i*horizon, (i+1)*horizon, 1):
                obs = s1[j].tolist()
                action = a1[j].tolist()
                next_obs = s2[j].tolist()
                reward = r[j].tolist()
                path.add_timestep(obs, action, next_obs, reward)
            paths.append(path)

        return paths

def get_data_from_offline_batch(params, env, normalization_scope=None, model='dynamics', split_ratio=0.9):
    train_collection = DataCollection(
        batch_size=params[model]['batch_size'],
        max_size=params['max_train_data'], shuffle=True)
    val_collection = DataCollection(batch_size=params[model]['batch_size'],
                                    max_size=params['max_val_data'],
                                    shuffle=False)
    rollout_sampler = RolloutSampler(env)
    # rl_paths = rollout_sampler.generate_offline_data(
    #        data_file=params['data_file'],
    #        n_train=params["n_train"]
    #    )
    rl_paths = rollout_sampler.generate_d4rl_data(
            dataset_name=params['data_file'],
            n_train=params["n_train"]
        )
    path_collection = PathCollection()
    obs_dim = env.observation_space.shape[0]
    normalization = add_path_data_to_collection_and_update_normalization(
        rl_paths, path_collection,
        train_collection, val_collection,
        normalization=None,
        split_ratio=split_ratio,
        obs_dim=obs_dim,
        normalization_scope=normalization_scope)
    return train_collection, val_collection, normalization, path_collection, rollout_sampler