Machine Learning, Optimization, and Data Science by Giuseppe Nicosia & Panos Pardalos & Giovanni Giuffrida & Renato Umeton & Vincenzo Sciacca

Author:Giuseppe Nicosia & Panos Pardalos & Giovanni Giuffrida & Renato Umeton & Vincenzo Sciacca
Language: eng
Format: epub
ISBN: 9783030137090
Publisher: Springer International Publishing

4.5 Hyper-parameters Tuning

Each episode lasts at most 500 steps/actions, and it may end either achieving success (i.e. descending the stairs), or reaching the steps limit. Thus, the death state is impossible for the agent, since in our experiments monsters and traps have been disabled and 500 steps are not enough to die for starvation.

Most of the remaining hyper-parameters values we adopted (for example the entropy ) came from [14], an Open-Source implementation of [9], except the following:

We employed the same Tensorflow’s RMSprop optimizer [1] available in [14], with parameters:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.