Create README.md

README.md

@@ -0,0 +1,20 @@
+---
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- decision-transformer
+- gym-continous-control
+
+---
+# 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 Hopper 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.
+