MTRF/r3l/r3l/r3l_agents/softlearning/evaluation_scripts/phased_evals_pickup.py [29:53]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    policy = get_policy_from_variant(variant, env)
    policy.set_weights(pickup_params)
    return wrap_policy(policy)

def wrap_policy(policy):
    def wrapped_policy(obs_dict):
        feed_dict = {
            key: obs_dict[key][None, ...]
            for key in policy.observation_keys
        }
        observation = flatten_input_structure(feed_dict)
        with policy.set_deterministic(True):
            action = policy.actions_np(observation)[0]
        return action
    return wrapped_policy

def do_evals(seed_dir, checkpoints_to_load=None, image_size=(512, 512)):
    print(seed_dir, "\n")
    path = Path(seed_dir)
    checkpoint_dirs = [d for d in glob.glob(str(path / "*")) if 'checkpoint' in d and os.path.isdir(d)]
    checkpoint_dirs.sort(key=lambda s: int(s.split("_")[-1]))
    if checkpoints_to_load:
        checkpoint_dirs = [d for d in checkpoint_dirs if int(d.split("_")[-1]) in checkpoints_to_load]

    N_EVAL_EPISODES = 1
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



MTRF/r3l/r3l/r3l_agents/softlearning/evaluation_scripts/video_collection_flipup_evals.py [36:60]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    policy = get_policy_from_variant(variant, env)
    policy.set_weights(pickup_params)
    return wrap_policy(policy)

def wrap_policy(policy):
    def wrapped_policy(obs_dict):
        feed_dict = {
            key: obs_dict[key][None, ...]
            for key in policy.observation_keys
        }
        observation = flatten_input_structure(feed_dict)
        with policy.set_deterministic(True):
            action = policy.actions_np(observation)[0]
        return action
    return wrapped_policy

def do_evals(seed_dir, checkpoints_to_load=None, image_size=(512, 512)):
    print(seed_dir, "\n")
    path = Path(seed_dir)
    checkpoint_dirs = [d for d in glob.glob(str(path / "*")) if 'checkpoint' in d and os.path.isdir(d)]
    checkpoint_dirs.sort(key=lambda s: int(s.split("_")[-1]))
    if checkpoints_to_load:
        checkpoint_dirs = [d for d in checkpoint_dirs if int(d.split("_")[-1]) in checkpoints_to_load]

    N_EVAL_EPISODES = 1
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -