This paper views the learning path recommendation task as a sequential decision problem and considers Partially Observable Markov Decision Process (POMDP) as an adequate approach. Although models of learners' memory strength have been proposed in the literature and used to promote review in recommendations, little work has been conducted for POMDP-based recommendation, and the models proposed are complex and data intensive. Our work proposes M-POMDP, a POMDP-based recommendation model that manages learners' memory strength, while limiting the increase in complexity and data required. M-POMDP has been evaluated on two real datasets. Experiments confirm that learners' memory strength can be managed with a limited increase in complexity, resulting in a higher precision of the recommendations, including for a medium-size dataset.