|
--- |
|
tags: |
|
- deep-reinforcement-learning |
|
- reinforcement-learning |
|
- decision-transformer |
|
- gym-continous-control |
|
|
|
pipeline_tag: reinforcement-learning |
|
|
|
--- |
|
# Decision Transformer model trained on medium-replay trajectories sampled from the Gym Walker2d environment |
|
This is a trained [Decision Transformer](https://arxiv.org/abs/2106.01345) model trained on medium-replay trajectories sampled from the Gym Walker2d environment |
|
|
|
<video src="https://huggingface.co/edbeeching/decision-transformer-gym-walker2d-medium-replay/resolve/main/walker2d-medium-replay.mp4" controls autoplay loop></video> |
|
|
|
The following normlization coeficients are required to use this model: |
|
|
|
mean = [1.2093647, 0.13264023, -0.14371201, -0.20465161, 0.55776125, -0.03231537, -0.2784661, 0.19130707, 1.4701707, -0.12504704, 0.05649531, -0.09991033, -0.34034026, 0.03546293, -0.08934259, -0.2992438, -0.5984178 ] |
|
|
|
std = [0.11929835, 0.3562574, 0.258522, 0.42075422, 0.5202291, 0.15685083, 0.3677098, 0.7161388, 1.3763766, 0.8632222, 2.6364644, 3.0134118, 3.720684, 4.867284, 2.6681626, 3.845187, 5.47683867] |
|
See our [Blog Post](https://colab.research.google.com/drive/1K3UuajwoPY1MzRKNkONNRS3gS5DxZ-qF?usp=sharing), [Colab notebook](https://colab.research.google.com/drive/1K3UuajwoPY1MzRKNkONNRS3gS5DxZ-qF?usp=sharing) or [Example Script](https://github.com/huggingface/transformers/tree/main/examples/research_projects/decision_transformer) for usage. |
|
|
|
|