Python tf_util.save_variables方法代码示例

# 需要导入模块: from baselines.common import tf_util [as 别名]
# 或者: from baselines.common.tf_util import save_variables [as 别名]
def initialize(self, sess):
        self.sess = sess
        self.sess.run(tf.global_variables_initializer())
        self.save = functools.partial(save_variables, sess=self.sess)
        self.load = functools.partial(load_variables, sess=self.load)
        self.actor_optimizer.sync()
        self.critic_optimizer.sync()
        self.sess.run(self.target_init_updates) 

# 需要导入模块: from baselines.common import tf_util [as 别名]
# 或者: from baselines.common.tf_util import save_variables [as 别名]
def learn(env, policy_func, dataset, optim_batch_size=128, max_iters=1e4,
          adam_epsilon=1e-5, optim_stepsize=3e-4,
          ckpt_dir=None, log_dir=None, task_name=None,
          verbose=False):

    val_per_iter = int(max_iters/10)
    ob_space = env.observation_space
    ac_space = env.action_space
    pi = policy_func("pi", ob_space, ac_space)  # Construct network for new policy
    # placeholder
    ob = U.get_placeholder_cached(name="ob")
    ac = pi.pdtype.sample_placeholder([None])
    stochastic = U.get_placeholder_cached(name="stochastic")
    loss = tf.reduce_mean(tf.square(ac-pi.ac))
    var_list = pi.get_trainable_variables()
    adam = MpiAdam(var_list, epsilon=adam_epsilon)
    lossandgrad = U.function([ob, ac, stochastic], [loss]+[U.flatgrad(loss, var_list)])

    U.initialize()
    adam.sync()
    logger.log("Pretraining with Behavior Cloning...")
    for iter_so_far in tqdm(range(int(max_iters))):
        ob_expert, ac_expert = dataset.get_next_batch(optim_batch_size, 'train')
        train_loss, g = lossandgrad(ob_expert, ac_expert, True)
        adam.update(g, optim_stepsize)
        if verbose and iter_so_far % val_per_iter == 0:
            ob_expert, ac_expert = dataset.get_next_batch(-1, 'val')
            val_loss, _ = lossandgrad(ob_expert, ac_expert, True)
            logger.log("Training loss: {}, Validation loss: {}".format(train_loss, val_loss))

    if ckpt_dir is None:
        savedir_fname = tempfile.TemporaryDirectory().name
    else:
        savedir_fname = osp.join(ckpt_dir, task_name)
    U.save_variables(savedir_fname, variables=pi.get_variables())
    return savedir_fname 

# 需要导入模块: from baselines.common import tf_util [as 别名]
# 或者: from baselines.common.tf_util import save_variables [as 别名]
def save(self, save_path):
        tf_util.save_variables(save_path) 

# 需要导入模块: from baselines.common import tf_util [as 别名]
# 或者: from baselines.common.tf_util import save_variables [as 别名]
def __init__(self, policy, env, nsteps,
            ent_coef=0.01, vf_coef=0.5, max_grad_norm=0.5, lr=7e-4,
            alpha=0.99, epsilon=1e-5, total_timesteps=int(80e6), lrschedule='linear'):

        sess = tf_util.get_session()
        nenvs = env.num_envs
        nbatch = nenvs*nsteps


        with tf.variable_scope('a2c_model', reuse=tf.AUTO_REUSE):
            step_model = policy(nenvs, 1, sess)
            train_model = policy(nbatch, nsteps, sess)

        A = tf.placeholder(train_model.action.dtype, train_model.action.shape)
        ADV = tf.placeholder(tf.float32, [nbatch])
        R = tf.placeholder(tf.float32, [nbatch])
        LR = tf.placeholder(tf.float32, [])

        neglogpac = train_model.pd.neglogp(A)
        entropy = tf.reduce_mean(train_model.pd.entropy())

        pg_loss = tf.reduce_mean(ADV * neglogpac)
        vf_loss = losses.mean_squared_error(tf.squeeze(train_model.vf), R)

        loss = pg_loss - entropy*ent_coef + vf_loss * vf_coef

        params = find_trainable_variables("a2c_model")
        grads = tf.gradients(loss, params)
        if max_grad_norm is not None:
            grads, grad_norm = tf.clip_by_global_norm(grads, max_grad_norm)
        grads = list(zip(grads, params))
        trainer = tf.train.RMSPropOptimizer(learning_rate=LR, decay=alpha, epsilon=epsilon)
        _train = trainer.apply_gradients(grads)

        lr = Scheduler(v=lr, nvalues=total_timesteps, schedule=lrschedule)

        def train(obs, states, rewards, masks, actions, values):
            advs = rewards - values
            for step in range(len(obs)):
                cur_lr = lr.value()

            td_map = {train_model.X:obs, A:actions, ADV:advs, R:rewards, LR:cur_lr}
            if states is not None:
                td_map[train_model.S] = states
                td_map[train_model.M] = masks
            policy_loss, value_loss, policy_entropy, _ = sess.run(
                [pg_loss, vf_loss, entropy, _train],
                td_map
            )
            return policy_loss, value_loss, policy_entropy


        self.train = train
        self.train_model = train_model
        self.step_model = step_model
        self.step = step_model.step
        self.value = step_model.value
        self.initial_state = step_model.initial_state
        self.save = functools.partial(tf_util.save_variables, sess=sess)
        self.load = functools.partial(tf_util.load_variables, sess=sess)
        tf.global_variables_initializer().run(session=sess)