Code to reproduce Deep 'Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization'.

1. Install MuJoCo at ~/.mujoco and copy the license key to ~/.mujoco/mjkey.txt.
2. Clone this RL-POMBU.
3. Create a conda environment by running

conda env create -f environmen.yml

cd shells
./run_cheetah.sh

1. There is some obsolete code. We will refactor the code in winter vacation.
2. We provide a new version of the paper with the appendix in arxiv.