In recent years, decimeter-level accuracy in WiFi indoor localization has become attainable within controlled environments. However, existing methods encounter challenges in maintaining robustness in more complex indoor environments: angle-based methods are compromised by the significant localization errors due to unreliable Angle of Arrival (AoA) estimations, and fingerprint-based methods suffer from performance degradation due to environmental changes. In this paper, we propose RLoc, a learning-based system designed for reliable localization and tracking. The key design principle of RLoc lies in quantifying the uncertainty level arises in the AoA estimation task and then exploiting the uncertainty to enhance the reliability of localization and tracking. To this end, RLoc first manually extracts the underutilized beamwidth feature via signal processing techniques. Then, it integrates the uncertainty quantification into neural network design through Kullback-Leibler (KL) divergence loss and ensemble techniques. Finally, these quantified uncertainties guide RLoc to optimally leverage the diversity of Access Points (APs) and the temporal continuous information of AoAs. Our experiments, evaluating on two datasets gathered from commercial off-the-shelf WiFi devices, demonstrate that RLoc surpasses state-of-the-art approaches by an average of 36.27% in in-domain scenarios and 20.40% in cross-domain scenarios.