Laixi Shi, Robert Dadashi, Yuejie Chi, Pablo Samuel Castro, Matthieu Geist. Offline Reinforcement Learning with On-Policy Q-Function Regularization. In Danai Koutra, Claudia Plant, Manuel Gomez-Rodriguez, Elena Baralis, Francesco Bonchi, editors, Machine Learning and Knowledge Discovery in Databases: Research Track - European Conference, ECML PKDD 2023, Turin, Italy, September 18-22, 2023, Proceedings, Part IV. Volume 14172 of Lecture Notes in Computer Science, pages 455-471, Springer, 2023. [doi]
@inproceedings{ShiDCCG23, title = {Offline Reinforcement Learning with On-Policy Q-Function Regularization}, author = {Laixi Shi and Robert Dadashi and Yuejie Chi and Pablo Samuel Castro and Matthieu Geist}, year = {2023}, doi = {10.1007/978-3-031-43421-1_27}, url = {https://doi.org/10.1007/978-3-031-43421-1_27}, researchr = {https://researchr.org/publication/ShiDCCG23}, cites = {0}, citedby = {0}, pages = {455-471}, booktitle = {Machine Learning and Knowledge Discovery in Databases: Research Track - European Conference, ECML PKDD 2023, Turin, Italy, September 18-22, 2023, Proceedings, Part IV}, editor = {Danai Koutra and Claudia Plant and Manuel Gomez-Rodriguez and Elena Baralis and Francesco Bonchi}, volume = {14172}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, isbn = {978-3-031-43421-1}, }