def mlp_actor_critic()

in spinup/algos/tf1/ppo/core.py [0:0]

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

def mlp_actor_critic(x, a, hidden_sizes=(64,64), activation=tf.tanh, 
                     output_activation=None, policy=None, action_space=None):

    # default policy builder depends on action space
    if policy is None and isinstance(action_space, Box):
        policy = mlp_gaussian_policy
    elif policy is None and isinstance(action_space, Discrete):
        policy = mlp_categorical_policy

    with tf.variable_scope('pi'):
        pi, logp, logp_pi = policy(x, a, hidden_sizes, activation, output_activation, action_space)
    with tf.variable_scope('v'):
        v = tf.squeeze(mlp(x, list(hidden_sizes)+[1], activation, None), axis=1)
    return pi, logp, logp_pi, v