FAST-Q: Fast-track Exploration with Adversarially Balanced State Representations for Counterfactual Action Estimation in Offline Reinforcement Learning.

@inproceedings{agrawal-2025-fastq, author = {Pulkit Agrawal and Rukma Talwadker and Aditya Pareek and Tridib Mukherjee}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{FAST-Q: Fast-track Exploration with Adversarially Balanced State Representations for Counterfactual Action Estimation in Offline Reinforcement Learning}}, booktitle = {{Companion Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025 - 2 May 2025}}, pages = {85--94}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3701716.3715224}, doi = {https://doi.org/10.1145/3701716.3715224} }