RicardoDominguez / PyCREPS

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

PyTorch and Theano implementations. #7

Closed RicardoDominguez closed 5 years ago

RicardoDominguez commented 5 years ago

Linear Gaussian model and dual function optimization using PyTorch and Theano. Only improves performance in sufficiently computationally expensive cases where the run time improvements offset the overheard introduced.