Hi MT,
To answer your two questions:
- The original A3C paper: https://arxiv.org/abs/1602.01783 contains an explanation of value and entropy regularization.
- Yep. It is just set to `1` in this case.
Hope that helps!
Hi MT,
To answer your two questions:
Hope that helps!
PhD. Interests include Deep (Reinforcement) Learning, Computational Neuroscience, and Phenomenology.
PhD. Interests include Deep (Reinforcement) Learning, Computational Neuroscience, and Phenomenology.