Accelerated Magnetic Resonance Imaging (MRI) requires careful optimization of k-space sampling patterns to balance acquisition speed and image quality. While recent advances in deep learning have shown promise in optimizing Cartesian sampling, the potential of reinforcement learning (RL) for non-Cartesian trajectory optimization remains largely unexplored. In this work, we present a novel RL framework for optimizing radial sampling trajectories in cardiac MRI. Our approach features a dual-branch architecture that jointly processes k-space and image-domain information, incorporating a cross-attention fusion mechanism to facilitate effective information exchange between domains. The framework employs an anatomically-aware reward design and a golden-ratio sampling strategy to ensure uniform k-space coverage while preserving cardiac structural details. Experimental results demonstrate that our method effectively learns optimal radial sampling strategies across multiple acceleration factors, achieving improved reconstruction quality compared to conventional approaches. Code available: https://github.com/Ruru-Xu/RL-kspace-Radial-Sampling