tf_agents/bandits/networks/heteroscedastic_q_network.py [105:125]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    action_spec = tf.nest.flatten(action_spec)[0]
    num_actions = action_spec.maximum - action_spec.minimum + 1
    encoder_input_tensor_spec = input_tensor_spec

    encoder = encoding_network.EncodingNetwork(
        encoder_input_tensor_spec,
        preprocessing_layers=preprocessing_layers,
        preprocessing_combiner=preprocessing_combiner,
        conv_layer_params=conv_layer_params,
        fc_layer_params=fc_layer_params,
        dropout_layer_params=dropout_layer_params,
        activation_fn=activation_fn,
        kernel_initializer=kernel_initializer,
        batch_squash=batch_squash,
        dtype=dtype)

    q_value_layer = tf.keras.layers.Dense(
        num_actions,
        activation=None,
        kernel_initializer=tf.random_uniform_initializer(
            minval=-0.03, maxval=0.03),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tf_agents/networks/q_network.py [100:120]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    action_spec = tf.nest.flatten(action_spec)[0]
    num_actions = action_spec.maximum - action_spec.minimum + 1
    encoder_input_tensor_spec = input_tensor_spec

    encoder = encoding_network.EncodingNetwork(
        encoder_input_tensor_spec,
        preprocessing_layers=preprocessing_layers,
        preprocessing_combiner=preprocessing_combiner,
        conv_layer_params=conv_layer_params,
        fc_layer_params=fc_layer_params,
        dropout_layer_params=dropout_layer_params,
        activation_fn=activation_fn,
        kernel_initializer=kernel_initializer,
        batch_squash=batch_squash,
        dtype=dtype)

    q_value_layer = tf.keras.layers.Dense(
        num_actions,
        activation=None,
        kernel_initializer=tf.random_uniform_initializer(
            minval=-0.03, maxval=0.03),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -