nrontsis / PILCO

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

Pr mountain car #30

Closed kyr-pol closed 4 years ago

kyr-pol commented 4 years ago

Added a simple task, the continuous mountain car, that doesn't require Mujoco to run. It's easy and quick to run and uses a normalisation wrapper that might be useful for other environments too.

nrontsis commented 4 years ago

Deprecated by #45