Follow
Ehsan Imani
Title
Cited by
Cited by
Year
An off-policy policy gradient theorem using emphatic weightings
E Imani, E Graves, M White
Advances in Neural Information Processing Systems 31, 2018
632018
Improving regression performance with distributional losses
E Imani, M White
International Conference on Machine Learning, 2157-2166, 2018
312018
Hallucinating Value: A Pitfall of Dyna-style Planning with Imperfect Environment Models
T Jafferjee, E Imani, E Talvitie, M White, M Bowling
arXiv preprint arXiv:2006.04363, 2020
152020
An implicit function learning approach for parametric modal regression
Y Pan, E Imani, A Farahmand, M White
Advances in Neural Information Processing Systems 33, 2020
62020
Multi-modal deep distance metric learning
SM Roostaiyan, E Imani, MS Baghshah
Intelligent Data Analysis 21 (6), 1351-1369, 2017
52017
Off-Policy Actor-Critic with Emphatic Weightings
E Graves, E Imani, R Kumaraswamy, M White
arXiv preprint arXiv:2111.08172, 2021
22021
Representation Alignment in Neural Networks
E Imani, W Hu, M White
1*
Label Alignment Regularization for Distribution Shift
E Imani, G Zhang, J Luo, P Poupart, Y Pan
arXiv preprint arXiv:2211.14960, 2022
2022
Understanding Feature Transfer Through Representation Alignment
E Imani, W Hu, M White
arXiv preprint arXiv:2112.07806, 2021
2021
Distributional Losses for Regression
E Imani
2019
The system can't perform the operation now. Try again later.
Articles 1–10