Question about setting network weights in POPLIN-P

[hzaskywalker]

Please correct me if I am wrong. In the Poplin-P AVG-R example, data_dict passed to train function of BC_WA_policy.policy_network contains the noise parameters searched by CEM and they can add the original network's weights to update policy network (eq 10 in the paper). But I don't find the code to add those two together. Could you please tell me how you update the network weights? Thanks!