def load_policy()

in safe_rl/utils/load_utils.py [0:0]

• 21 lines of code
• 11 McCabe index (conditional complexity)

def load_policy(fpath, itr='last', deterministic=False):

    # handle which epoch to load from
    if itr=='last':
        saves = [int(x[11:]) for x in os.listdir(fpath) if 'simple_save' in x and len(x)>11]
        itr = '%d'%max(saves) if len(saves) > 0 else ''
    else:
        itr = '%d'%itr

    # load the things!
    sess = tf.Session(graph=tf.Graph())
    model = restore_tf_graph(sess, osp.join(fpath, 'simple_save'+itr))

    # get the correct op for executing actions
    if deterministic and 'mu' in model.keys():
        # 'deterministic' is only a valid option for SAC policies
        print('Using deterministic action op.')
        action_op = model['mu']
    else:
        print('Using default action op.')
        action_op = model['pi']

    # make function for producing an action given a single state
    get_action = lambda x : sess.run(action_op, feed_dict={model['x']: x[None,:]})[0]

    # try to load environment from save
    # (sometimes this will fail because the environment could not be pickled)
    try:
        state = joblib.load(osp.join(fpath, 'vars'+itr+'.pkl'))
        env = state['env']
    except:
        env = None

    return env, get_action, sess