Update README.md
Browse files
README.md
CHANGED
@@ -71,5 +71,22 @@ action = model.step(obs, goal)
|
|
71 |
- **Learning Rate**: 0.0001
|
72 |
- **Weight Decay**: 0.05
|
73 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
## License
|
75 |
This model is released under the MIT license.
|
|
|
71 |
- **Learning Rate**: 0.0001
|
72 |
- **Weight Decay**: 0.05
|
73 |
|
74 |
+
|
75 |
+
## Citation
|
76 |
+
|
77 |
+
If you found the code usefull, please cite our work:
|
78 |
+
|
79 |
+
```bibtex
|
80 |
+
@misc{reuss2024efficient,
|
81 |
+
title={Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning},
|
82 |
+
author={Moritz Reuss and Jyothish Pari and Pulkit Agrawal and Rudolf Lioutikov},
|
83 |
+
year={2024},
|
84 |
+
eprint={2412.12953},
|
85 |
+
archivePrefix={arXiv},
|
86 |
+
primaryClass={cs.LG}
|
87 |
+
}
|
88 |
+
```
|
89 |
+
|
90 |
+
|
91 |
## License
|
92 |
This model is released under the MIT license.
|