World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios like autonomous driving, noncontrollable dynamics that are independent or sparsely dependent on action signals often exist, making it challenging to learn effective world models. To address this issue, we propose Iso-Dream++, a model-based reinforcement learning approach that has two main contributions. First, we optimize the inverse dynamics to encourage the world model to isolate controllable state transitions from the mixed spatiotemporal variations of the environment. Second, we perform policy optimization based on the decoupled latent imaginations, where we roll out noncontrollable states into the future and adaptively associate them with the current controllable state. This enables long-horizon visuomotor control tasks to benefit from isolating mixed dynamics sources in the wild, such as self-driving cars that can anticipate the movement of other vehicles, thereby avoiding potential risks. On top of our previous work [1], we further consider the sparse dependencies between controllable and noncontrollable states, address the training collapse problem of state decoupling, and validate our approach in transfer learning setups. Our empirical study demonstrates that Iso-Dream++ outperforms existing reinforcement learning models significantly on CARLA and DeepMind Control.

Objective: To evaluate the relationship between interatrial septal thickness (IAST) and left atrial geometry in patients with rheumatic mitral stenosis (RMD), as measured by transesophageal and transthoracic echocardiography. Methods: Transesophageal and transthoracic echocardiograms were used to detect IAST and left atrial geometry respectively in 100 patients. Results: IAST and interatrial septal thickening fraction (IASTF) were significantly different in patients with different degrees of mitral stenosis. The left atrial volume change fraction (LAVCF) and IASTF were positively correlated (r = 0.766, P < 0.001). Conclusion: There is important clinical significance for transesophageal and transthoracic echocardiography in evaluating the relationship between IAST and left atrial geometry, IAST and IASTF can reflect the changes in left atrial geometry