IEEE 802.11ax high-throughput wireless access networks support multi-user multiple-input multiple-output (MU-MIMO)-based communication, where a set of spatially apart wireless stations forms a user group and uses different spatial streams for simultaneous transmission and reception. In this architecture, dynamic user group selection is an important aspect for maintaining high-throughput fair channel access. In addition, the physical and media access control parameters, like channel bonding levels, modulation, and coding schemes need to be tuned based on the selected user group to utilize the maximum available capacity. In this paper, we design an online learning-based approach over a centralized logical control architecture, called intelligent MU-MIMO user selection with link adaptation (IMMULA), where a central controller collects the performance statistics under various configuration space and applies a reinforcement learning strategy to select the best-suited configurations dynamically at periodic intervals. The performance of IMMULA is analyzed over a testbed consisting of 6 IEEE 802.11ac access points and 20 wireless stations. The results show that IMMULA improves network performances significantly compared to other baseline mechanisms.