The performance of wireless remote state estimation depends on the wireless channel quality, and hence is vulnerable to wireless channel jamming attack. In this paper, we investigate the problem of optimal jamming attack schedule that causes the largest performance degradation to the remote state estimation system. Unlike many previous studies, we consider that the sensor transmit data to the remote estimator through one of multiple independent wireless channels. Due to radio constraint of the attacker, we assume that it can only launch jamming attack on one of the channels at each step. We propose a matrix game approach to model the interactions between the attacker and the sensor and theoretically prove the existence of an optimal attack strategy. We further design an online algorithm based on temporal-difference learning for the attacker to make attack decisions. Numerical examples are provided to demonstrate the effectiveness of the game theoretical method.