A unified Performance-Based Seismic Design (PBSD) procedure is proposed and successfully implemented. It provides an alternative to the currently used life safety design requirement. To successfully develop the concept, structures are represented by finite elements and excited by the seismic loading in time domain. A novel reliability evaluation procedure is proposed for such representation. An improved response surface based procedure is proposed by combining it with the First-Order Reliability Method (FORM) and the appropriate response surfaces are constructed by combining the saturated design and the central composite design sampling schemes. Performances are defined in terms of Collapse Prevention (CP), Life Safety (LS), and Immediate Occupancy (IO), as commonly used in the profession. The corresponding risks are evaluated by exciting a 9-story steel frame designed by experts satisfying all post-Northridge seismic design requirements. It was excited by 20 earthquake time histories for each

No abstract

No abstract

No abstract

Learning optimal policies in real-world domains with delayed rewards is a major challenge in Reinforcement Learning. We address the credit assignment problem by proposing a Gaussian Process (GP)-based immediate reward approximation algorithm and evaluate its effectiveness in 4 contexts where rewards can be delayed for long trajectories. In one GridWorld game and 8 Atari games, where immediate rewards are available, our results showed that on 7 out 9 games, the proposed GP-inferred reward policy performed at least as well as the immediate reward policy and significantly outperformed the corresponding delayed reward policy. In e-learning and healthcare applications, we combined GP-inferred immediate rewards with offline Deep Q-Network (DQN) policy induction and showed that the GP-inferred reward policies outperformed the policies induced using delayed rewards in both real-world contexts.