Run trained policies for active human environments on static human environments about assistive-gym HOT 2 CLOSED

def setup_config(env, algo, coop=False, seed=0, extra_configs={}):
    num_processes = multiprocessing.cpu_count()
    if algo == 'ppo':
        config = ppo.DEFAULT_CONFIG.copy()
        config['train_batch_size'] = 19200
        config['num_sgd_iter'] = 50
        config['sgd_minibatch_size'] = 128
        config['lambda'] = 0.95
        config['model']['fcnet_hiddens'] = [100, 100]
    elif algo == 'sac':
        # NOTE: pip3 install tensorflow_probability
        config = sac.DEFAULT_CONFIG.copy()
        config['timesteps_per_iteration'] = 400
        config['learning_starts'] = 1000
        config['Q_model']['fcnet_hiddens'] = [100, 100]
        config['policy_model']['fcnet_hiddens'] = [100, 100]
        # config['normalize_actions'] = False
    config['num_workers'] = num_processes
    config['num_cpus_per_worker'] = 0
    config['seed'] = seed
    config['log_level'] = 'ERROR'
    # if algo == 'sac':
    #     config['num_workers'] = 1

   # HERE THE CHANGES
    obs = env.reset()
    config['observation_space'] = env.observation_space_robot
    config['action_space'] = env.action_space_robot
   
   
    # if coop:
    #     obs = env.reset()
    #     policies = {'robot': (None, env.observation_space_robot, env.action_space_robot, {}), 'human': (None, env.observation_space_human, env.action_space_human, {})}
    #     config['multiagent'] = {'policies': policies, 'policy_mapping_fn': lambda a: a}
    #     config['env_config'] = {'num_agents': 2}
    return {**config, **extra_configs}