def build_act_with_param_noise()

in baselines/deepq/build_graph.py [0:0]


def build_act_with_param_noise(make_obs_ph, q_func, num_actions, scope="deepq", reuse=None, param_noise_filter_func=None):
    """Creates the act function with support for parameter space noise exploration (https://arxiv.org/abs/1706.01905):

    Parameters
    ----------
    make_obs_ph: str -> tf.placeholder or TfInput
        a function that take a name and creates a placeholder of input with that name
    q_func: (tf.Variable, int, str, bool) -> tf.Variable
        the model that takes the following inputs:
            observation_in: object
                the output of observation placeholder
            num_actions: int
                number of actions
            scope: str
            reuse: bool
                should be passed to outer variable scope
        and returns a tensor of shape (batch_size, num_actions) with values of every action.
    num_actions: int
        number of actions.
    scope: str or VariableScope
        optional scope for variable_scope.
    reuse: bool or None
        whether or not the variables should be reused. To be able to reuse the scope must be given.
    param_noise_filter_func: tf.Variable -> bool
        function that decides whether or not a variable should be perturbed. Only applicable
        if param_noise is True. If set to None, default_param_noise_filter is used by default.

    Returns
    -------
    act: (tf.Variable, bool, float, bool, float, bool) -> tf.Variable
        function to select and action given observation.
`       See the top of the file for details.
    """
    if param_noise_filter_func is None:
        param_noise_filter_func = default_param_noise_filter

    with tf.variable_scope(scope, reuse=reuse):
        observations_ph = make_obs_ph("observation")
        stochastic_ph = tf.placeholder(tf.bool, (), name="stochastic")
        update_eps_ph = tf.placeholder(tf.float32, (), name="update_eps")
        update_param_noise_threshold_ph = tf.placeholder(tf.float32, (), name="update_param_noise_threshold")
        update_param_noise_scale_ph = tf.placeholder(tf.bool, (), name="update_param_noise_scale")
        reset_ph = tf.placeholder(tf.bool, (), name="reset")

        eps = tf.get_variable("eps", (), initializer=tf.constant_initializer(0))
        param_noise_scale = tf.get_variable("param_noise_scale", (), initializer=tf.constant_initializer(0.01), trainable=False)
        param_noise_threshold = tf.get_variable("param_noise_threshold", (), initializer=tf.constant_initializer(0.05), trainable=False)

        # Unmodified Q.
        q_values = q_func(observations_ph.get(), num_actions, scope="q_func")

        # Perturbable Q used for the actual rollout.
        q_values_perturbed = q_func(observations_ph.get(), num_actions, scope="perturbed_q_func")
        # We have to wrap this code into a function due to the way tf.cond() works. See
        # https://stackoverflow.com/questions/37063952/confused-by-the-behavior-of-tf-cond for
        # a more detailed discussion.
        def perturb_vars(original_scope, perturbed_scope):
            all_vars = scope_vars(absolute_scope_name(original_scope))
            all_perturbed_vars = scope_vars(absolute_scope_name(perturbed_scope))
            assert len(all_vars) == len(all_perturbed_vars)
            perturb_ops = []
            for var, perturbed_var in zip(all_vars, all_perturbed_vars):
                if param_noise_filter_func(perturbed_var):
                    # Perturb this variable.
                    op = tf.assign(perturbed_var, var + tf.random_normal(shape=tf.shape(var), mean=0., stddev=param_noise_scale))
                else:
                    # Do not perturb, just assign.
                    op = tf.assign(perturbed_var, var)
                perturb_ops.append(op)
            assert len(perturb_ops) == len(all_vars)
            return tf.group(*perturb_ops)

        # Set up functionality to re-compute `param_noise_scale`. This perturbs yet another copy
        # of the network and measures the effect of that perturbation in action space. If the perturbation
        # is too big, reduce scale of perturbation, otherwise increase.
        q_values_adaptive = q_func(observations_ph.get(), num_actions, scope="adaptive_q_func")
        perturb_for_adaption = perturb_vars(original_scope="q_func", perturbed_scope="adaptive_q_func")
        kl = tf.reduce_sum(tf.nn.softmax(q_values) * (tf.log(tf.nn.softmax(q_values)) - tf.log(tf.nn.softmax(q_values_adaptive))), axis=-1)
        mean_kl = tf.reduce_mean(kl)
        def update_scale():
            with tf.control_dependencies([perturb_for_adaption]):
                update_scale_expr = tf.cond(mean_kl < param_noise_threshold,
                    lambda: param_noise_scale.assign(param_noise_scale * 1.01),
                    lambda: param_noise_scale.assign(param_noise_scale / 1.01),
                )
            return update_scale_expr

        # Functionality to update the threshold for parameter space noise.
        update_param_noise_threshold_expr = param_noise_threshold.assign(tf.cond(update_param_noise_threshold_ph >= 0,
            lambda: update_param_noise_threshold_ph, lambda: param_noise_threshold))

        # Put everything together.
        deterministic_actions = tf.argmax(q_values_perturbed, axis=1)
        batch_size = tf.shape(observations_ph.get())[0]
        random_actions = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=num_actions, dtype=tf.int64)
        chose_random = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=1, dtype=tf.float32) < eps
        stochastic_actions = tf.where(chose_random, random_actions, deterministic_actions)

        output_actions = tf.cond(stochastic_ph, lambda: stochastic_actions, lambda: deterministic_actions)
        update_eps_expr = eps.assign(tf.cond(update_eps_ph >= 0, lambda: update_eps_ph, lambda: eps))
        updates = [
            update_eps_expr,
            tf.cond(reset_ph, lambda: perturb_vars(original_scope="q_func", perturbed_scope="perturbed_q_func"), lambda: tf.group(*[])),
            tf.cond(update_param_noise_scale_ph, lambda: update_scale(), lambda: tf.Variable(0., trainable=False)),
            update_param_noise_threshold_expr,
        ]
        _act = U.function(inputs=[observations_ph, stochastic_ph, update_eps_ph, reset_ph, update_param_noise_threshold_ph, update_param_noise_scale_ph],
                         outputs=output_actions,
                         givens={update_eps_ph: -1.0, stochastic_ph: True, reset_ph: False, update_param_noise_threshold_ph: False, update_param_noise_scale_ph: False},
                         updates=updates)
        def act(ob, reset=False, update_param_noise_threshold=False, update_param_noise_scale=False, stochastic=True, update_eps=-1):
            return _act(ob, stochastic, update_eps, reset, update_param_noise_threshold, update_param_noise_scale)
        return act