Create README.md

README.md

@@ -0,0 +1,21 @@
+---
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- decision-transformer
+- gym-continous-control
+
+---
+# Decision Transformer model trained on expert trajectories sampled from the Gym HalfCheetah environment
+This is a trained [Decision Transformer](https://arxiv.org/abs/2106.01345) model trained on expert trajectories sampled from the Gym Hopper environment
+
+<video src="https://huggingface.co/edbeeching/decision-transformer-gym-halfcheetah-expert/resolve/main/halfcheetah-expert.mp4" controls autoplay loop></video>
+
+The following normlization coeficients are required to use this model:
+
+mean = [ -0.04489148,  0.03232588,  0.06034835, -0.17081226, -0.19480659, -0.05751596,  0.09701628,  0.03239211, 11.047426,   -0.07997331, -0.32363534,  0.36297753,  0.42322603,  0.40836546,  1.1085187,  -0.4874403,  -0.0737481 ] 
+
+std = [0.04002118,  0.4107858, 0.54217845,  0.41522816, 0.23796624, 0.62036866, 0.30100912,  0.21737163, 2.2105937, 0.572586, 1.7255033, 11.844218, 12.06324,     7.0495934,  13.499867, 7.195647, 5.0264325]
+
+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.
+