{{Cite journal| doi = 10.1007/s00521-023-09029-3| issn = 0941-0643 1433-3058| volume = 36| issue = 2| pages = 585–598| last1 = Hêche| first1 = Félicien| last2 = Barakat| first2 = Oussama| last3 = Desmettre| first3 = Thibaut| last4 = Marx| first4 = Tania| last5 = Robert-Nicoud| first5 = Stephan| title = Offline reinforcement learning in high-dimensional stochastic environments| journal = Neural Computing and Applications| date = 2024-01-01}}