search

RicardoDominguez / PyCREPS

Contextual Relative Entropy Policy Search for Reinforcement Learning in Python
15 stars 1 forks source link

Improve linear gaussian model policy update #9

Closed RicardoDominguez closed 6 years ago

RicardoDominguez commented 6 years ago

The covariance matrix is now computed directly through matrix multiplication, without any loops.

Addresses #3 and #5