sawcordwell / pymdptoolbox

Markov Decision Process (MDP) Toolbox for Python
BSD 3-Clause "New" or "Revised" License
518 stars 252 forks source link

Add ability to use custom learning rate #31

Open JSPromisel opened 5 years ago

JSPromisel commented 5 years ago

Allow users to adjust the learning rate for Q learning. This way users can explicitly choose between exploration and exploitation focused learning.

coveralls commented 5 years ago

Coverage Status

Coverage increased (+0.008%) to 86.838% when pulling e566a7964b670318c98194c0d430c2c89f47ae92 on JSPromisel:add-custom-learn-rate into 7c96789cc80e280437005c12065cf70266c11636 on sawcordwell:master.