Know what it does not know: Improving Offline Deep Reinforcement Learning with Uncertainty Estimation

Offline reinforcement learning, or learning from a fixed data set, is an attractive alternative to online reinforcement learning. Offline reinforcement learning promises to address the cost and safety implications of taking numerous random or bad actions online, which is a crucial aspect of traditional reinforcement learning that makes it...

Towards a standardized statistical correction between RANSe-based full-scale CFD and sea trial measurement

This research considers Amels LE and SX super yachts. Bare hull, appended hull, and actuator disk simulations were performed using CFD, and compared to sea trial results. The results of the CFD are unique because they were generated after the sea trials were conducted, resulting in the ship speed in CFD and sea trial being similar. The results...

The role of DSSs in decision-making processes characterized by time pressure, uncertainty and dynamism: an agent-based modeling approach

The effect of using decision support systems in decision-making processes characterized by time pressure, uncertainty, and dynamism is still very limited and debated among researchers. By utilizing a case study that concerns the employment of a DSS to assist the procedures of intercepting fugitives undertaken by the Dutch National Police, this...

Impact of leader-follower behavior on evacuation performance: An exploratory modeling approach

Different leader-follower behavior may be observed in models, such as group gathering, backtracking, and flexibility of the group. However, a comparison of these behaviors resulting in possible substantially different estimates of optimal evacuation procedures is lacking. Hence, we developed an Agent-based model in combination with exploratory...

Visualization of Fiber Tract Uncertainty during Neurosurgery

In modern neurosurgical practice, a surgeon can see a patient’s fiber tracts (nerve tracts) on a monitor in the operating room. This design study investigates the benefit of adding the uncertainty of the tracts and aims to improve the surgeon’s orientation while reducing visual clutter.<br/><br/>Based on an interview with a neurosurgeon and our...

Shared Mobility-on-Demand Systems: Reducing service unreliability

On-demand ridesharing might be an effective solution to reduce traffic congestion and, as a result, reduce emissions to mitigate environmental issues. However, travel times are more uncertain in ridesharing services compared to non-shared transit services due to their shared nature. For example, at one moment, the users are informed that the...