Ali Ezzeddine, Nafee Mourad, Babak Nadjar Araabi, Majid Nili Ahmadabadi. Combination of learning from non-optimal demonstrations and feedbacks using inverse reinforcement learning and Bayesian policy improvement. Expert Syst. Appl., 112:331-341, 2018. [doi]
@article{EzzeddineMAA18,
title = {Combination of learning from non-optimal demonstrations and feedbacks using inverse reinforcement learning and Bayesian policy improvement},
author = {Ali Ezzeddine and Nafee Mourad and Babak Nadjar Araabi and Majid Nili Ahmadabadi},
year = {2018},
doi = {10.1016/j.eswa.2018.06.035},
url = {https://doi.org/10.1016/j.eswa.2018.06.035},
researchr = {https://researchr.org/publication/EzzeddineMAA18},
cites = {0},
citedby = {0},
journal = {Expert Syst. Appl.},
volume = {112},
pages = {331-341},
}