This is a Pytorch implementation of paper: Dreamer to control: Learning Behaviors by Latent Imagination. Get similar results compared with original Tensorflow implementation. Tested on dm_control suite, with tasks cartpole-balance, cheetah-run, and ball-in-cup_catch. Testing on more tasks is ongoing.
- Install
dm_controland MuJoCo: following DeepMind Control Suite and MuJoCo - Run
conda env create -f environment.ymlto install dependencies.
python3 dreamer.py --env [env-name]
More optional environments are listed in env.py . The code is only tested on dm_control suite. If you have any question, feel free to post issues.
- Robustness of action repeat
[1] Dream to Control: Learning Behaviors by Latent Imagination
[2] Tensorflow implementation, with tensorflow1.0
[3] Tensorflow implementation, with tensorflow2.0
[4] Learning Latent Dynamics for Planning from Pixels
[5] PlaNet implementation from @Kaixhin