We propose the first sound and complete learning-based compositional verification technique for probabilistic safety properties on concurrent systems where each component is an Markov decision process. Different from previous works, weighted assumptions are introduced to attain completeness of our framework. Since weighted assumptions can be implicitly represented by multi-terminal binary decision diagrams (MTBDD’s), we give an L∗ -based learning algorithm for MTBDD’s to infer weighted assumptions. Experimental results suggest promising outlooks for our compositional technique. Categories and Subject Descriptors D.2.4 [Software/Program Verification]: Model Checking General Terms Theory, Verification Keywords Compositional verification, probabilistic model checking, algorithmic learning