search

nrontsis / PILCO

Bayesian Reinforcement Learning in Tensorflow
MIT License
313 stars 84 forks source link

Use Matlab's implementation to train OpenAI gym tasks #14

Open nrontsis opened 5 years ago

nrontsis commented 5 years ago

This will allow easier debugging and comparison between the two implementations.

nrontsis commented 5 years ago

Calling python from Matlab is very limited (see also here), so the best way would be for Python to make multiple calls to Matlab, in the same way we do in the current unit tests.

This should be quite straightforward.