Vascular interventional robotic systems play a critical role in protecting physicians from X-ray radiation exposure during vascular surgery procedures. The AI-copilot autonomous delivering capability can further enhance physicians’ experience on robotic systems. However, extracting features from real-time X-ray image and generating operational decisions is challenging. Addressing these challenges, this paper proposed a X-ray simulation platform, which provides data and environments for pre-training vision encoders and training agent by reinforcement learning. This agent integrates pre-trained vision encoder for interventional instruments with actor-critic network. This paper validated the impact of different vision encoders, different feature fusion schemes, and different reinforcement learning methods on agent performance. The optimized solution demonstrated superior performance in simulation benchmarks and was successfully transferred to a real robotic system. Experiments demonstrate this method’s ability to generate effective strategies from real-time X-ray inputs and shows promising clinical robotics applications.