Zhang-Wei Hong, Pulkit Agrawal, Remi Tachet des Combes, Romain Laroche. Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. [doi]
@inproceedings{HongACL23,
title = {Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting},
author = {Zhang-Wei Hong and Pulkit Agrawal and Remi Tachet des Combes and Romain Laroche},
year = {2023},
url = {https://openreview.net/pdf?id=OhUAblg27z},
researchr = {https://researchr.org/publication/HongACL23},
cites = {0},
citedby = {0},
booktitle = {The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
}