diff --git a/README.md b/README.md index f767158..bfce688 100644 --- a/README.md +++ b/README.md @@ -7,6 +7,9 @@ PlaNet: A Deep Planning Network for Reinforcement Learning [[1]](#references). S Run with `python.main.py`. For best performance with DeepMind Control Suite, try setting environment variable `MUJOCO_GL=egl` (see instructions and details [here](https://github.com/deepmind/dm_control#rendering)). + +Results and pretrained models can be found in the [releases](https://github.com/Kaixhin/PlaNet/releases). + Requirements ------------ @@ -17,7 +20,7 @@ Requirements - [Plotly](https://plot.ly/) - [PyTorch](http://pytorch.org/) -To install all dependencies with Anaconda run `conda env create -f environment.yml` and use `source activate rainbow` to activate the environment. +To install all dependencies with Anaconda run `conda env create -f environment.yml` and use `source activate planet` to activate the environment. Links ----- @@ -25,6 +28,12 @@ Links - [Introducing PlaNet: A Deep Planning Network for Reinforcement Learning](https://ai.googleblog.com/2019/02/introducing-planet-deep-planning.html) - [google-research/planet](https://github.com/google-research/planet) +Acknowledgements +---------------- + +- [@danijar](https://github.com/danijar) for [google-research/planet](https://github.com/google-research/planet) and [help reproducing results](https://github.com/google-research/planet/issues/28) +- [@sg2](https://github.com/sg2) for [running experiments](https://github.com/Kaixhin/PlaNet/issues/9) + References ----------