Deep Planning Network: Control from pixels by latent planning with learned dynamics
PlaNet: A Deep Planning Network for Reinforcement Learning . Supports symbolic/visual observation spaces. Supports some Gym environments (including classic control/non-MuJoCo environments, so DeepMind Control Suite/MuJoCo are optional dependencies). Hyperparameters have been taken from the original work and are tuned for DeepMind Control Suite, so would need tuning for any other domains (such as the Gym environments).
python.main.py. For best performance with DeepMind Control Suite, try setting environment variable
MUJOCO_GL=egl(see instructions and details here).
Results and pretrained models can be found in the releases.
To install all dependencies with Anaconda run
conda env create -f environment.ymland use
source activate planetto activate the environment.