No policy loss - Githubissues

alshedivat / lola

Code release for Learning with Opponent-Learning Awareness and variations.

MIT License

145 stars 35 forks source link

Closed a7b23 closed 6 years ago

a7b23 commented 6 years ago

In the update step of the Pnetwork only the value loss is included in the total loss. Why is the policy loss not included in the total loss?

alshedivat commented 6 years ago

The loss that is being optimized is constructed in the corrections_func (see corrections.py).