Gao, G, Gao, Q, Yang, X, Ju, S, Pajic, M, and Chi, M. On Trajectory Augmentations for Off‑Policy Evaluation. Retrieved from https://par.nsf.gov/biblio/10609445.

Gao, G, Gao, Q, Yang, X, Ju, S, Pajic, M, & Chi, M. On Trajectory Augmentations for Off‑Policy Evaluation. Retrieved from https://par.nsf.gov/biblio/10609445.

Gao, G, Gao, Q, Yang, X, Ju, S, Pajic, M, and Chi, M. "On Trajectory Augmentations for Off‑Policy Evaluation". Country unknown/Code not available: Proceedings of the Twelfth International Conference on Learning Representations / OpenReview (ICLR). https://par.nsf.gov/biblio/10609445.

@article{osti_10609445,
place = {Country unknown/Code not available}, title = {On Trajectory Augmentations for Off‑Policy Evaluation}, url = {https://par.nsf.gov/biblio/10609445}, abstractNote = {Introduces OAT (Offline with Augmented Trajectories), a generative sub-trajectory augmentation method designed to enhance off-policy evaluation accuracy. Experiments across robotics, healthcare, and e-learning show substantial performance gains over baselines.}, journal = {}, publisher = {Proceedings of the Twelfth International Conference on Learning Representations / OpenReview (ICLR)}, author = {Gao, G and Gao, Q and Yang, X and Ju, S and Pajic, M and Chi, M}, }