TY - JOUR ID - 156030 TI - An overview of reinforcement learning and deep reinforcement learning for condition-based maintenance JO - International Journal of Reliability, Risk and Safety: Theory and Application JA - IJRRS LA - en SN - AU - Dehghani Ghobadi, Zahra AU - Haghighi, Firoozeh AU - safari, Abdollah AD - School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran, Tehran, Iran Y1 - 2021 PY - 2021 VL - 4 IS - 2 SP - 81 EP - 89 KW - Reinforcement Learning KW - Deep reinforcement learning KW - Condition-based Maintenance KW - Markov decision process DO - 10.30699/IJRRS.4.2.9 N2 - Condition-based maintenance (CBM) involves making decisions on maintenance based on the actual deterioration conditions of the components. It consists of a chain of states representing various stages of deterioration and a set of maintenance actions. Therefore, condition-based maintenance is a sequential decision-making problem. Reinforcement Learning(RL) is a subfield of Machine Learning proposed for automated decision-making. This article provides an overview of reinforcement learning and deep reinforcement learning methods that have been used so far in condition-based maintenance optimization. UR - http://www.ijrrs.com/article_156030.html L1 - http://www.ijrrs.com/article_156030_1dc572268b0f23bf37f1f19ab0f62eeb.pdf ER -