This paper studies the rolling security-constrained unit commitment (RSCUC) problem with AC power flow and uncertainties. For this NP-hard problem, it is modeled as a Markov decision process, which is then solved by a transfer-based approximate dynamic programming (TADP) algorithm proposed in this paper. Different from traditional approximate dynamic programming (ADP) algorithms, TADP can obtain the commitment states of most units in advance through a decision transfer technique, thus reducing the action space of TADP significantly. Moreover, compared with traditional ADP algorithms, which require to determine the commitment state of each unit, TADP only needs determine the unit with the smallest on-state probability among all on-state units, thus further reducing the action space. The proposed algorithm can also prevent the iterative update of value functions and the reliance on rolling forecast information, which makes more sense in the rolling decision-making process of RSCUC. Finally, numerical simulations are carried out on a modified IEEE 39-bus system and a real 2778-bus system to demonstrate the effectiveness of the proposed algorithm.