def mlp_categorical_policy()

in safe_rl/pg/network.py [0:0]

• 13 lines of code
• 1 McCabe index (conditional complexity)

def mlp_categorical_policy(x, a, hidden_sizes, activation, output_activation, action_space):
    act_dim = action_space.n
    logits = mlp(x, list(hidden_sizes)+[act_dim], activation, None)
    logp_all = tf.nn.log_softmax(logits)
    pi = tf.squeeze(tf.multinomial(logits,1), axis=1)
    logp = tf.reduce_sum(tf.one_hot(a, depth=act_dim) * logp_all, axis=1)
    logp_pi = tf.reduce_sum(tf.one_hot(pi, depth=act_dim) * logp_all, axis=1)

    old_logp_all = placeholder(act_dim)
    d_kl = categorical_kl(logp_all, old_logp_all)
    ent = categorical_entropy(logp_all)

    pi_info = {'logp_all': logp_all}
    pi_info_phs = {'logp_all': old_logp_all}

    return pi, logp, logp_pi, pi_info, pi_info_phs, d_kl, ent