Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization

Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization. Jeong, J., Wang, X., Gimelfarb, M., Kim, H., Abdulhai, B., & Sanner, S. In Proceedings of the International Conference on Learning Representations (ICLR-23), Kigali, Rwanda, 2023.

Paper

Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization [link]

Github bibtex 51 downloads

@inproceedings{sanner:iclr23,
	    title = {Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization},
	    author = {Jihwan Jeong and Xiaoyu Wang and Michael Gimelfarb and Hyunwoo Kim and Baher Abdulhai and Scott Sanner},
	    booktitle = {Proceedings of the International Conference on Learning Representations ({ICLR}-23)},
	    address = {Kigali, Rwanda},
	    year = {2023},
	    url_paper = {https://ssanner.github.io/papers/iclr23_cbop.pdf},
	    url_github = {https://github.com/jihwan-jeong/CBOP}
}

Downloads: 51