Abstract Achieving high-fidelity quantum gates is crucial for reliable quantum computing. However, decoherence and control pulse imperfections pose significant challenges in realizing the theoretical fidelity of quantum gates in practical systems. To address these challenges, we propose the meta-reinforcement learning quantum control algorithm (metaQctrl), which leverages a two-layer learning framework to enhance robustness and fidelity. The inner reinforcement learning network focuses on decision making for specific optimization problems, while the outer meta-learning network adapts to varying environments and provides feedback to the inner network. Our comparative analysis regarding the realization of universal quantum gates demonstrates that metaQctrl achieves higher fidelity with fewer control pulses than conventional methods in the presence of uncertainties. These results can contribute to the exploration of the quantum speed limit and facilitate the implementation of quantum circuits with system imperfections involved.