In this study, a real and significant industrial problem in a steam power plant was investigated. Reheater tubes in boilers are under the creep and the fireside corrosion mechanism that cause some of them to fail. Since the estimation of probability of failure (PoF) and remaining life (RL) is expensive and time consuming in the deterministic methods, in this work they were evaluated using struc...

1,+2.6XlO-“~X,2 I Ln,B,, dl. 0) rl in-phase components of the polarization angle modulation $. The method is insensitive to laser power variations and path length changes in the probe beam optical circuit and is robust to plasma refractive beam bending. Using a local oscillator derived from the Faraday rotated beam itself, the signals obtained at the two output ports can also be made proportion...

In many real-world situations a decision maker may make decisions across many separate reinforcement learning tasks in parallel, yet there has been very little work on concurrent RL. Building on the efficient exploration RL literature, we introduce two new concurrent RL algorithms and bound their sample complexity. We show that under some mild conditions, both when the agent is known to be acti...

The contribution of this paper is to introduce heuristics, that go beyond safe state abstraction in hierarchical reinforcement learning, to approximate a decomposed value function. Additional improvements in time and space complexity for learning and execution may outweigh achieving less than hierarchically optimal performance and deliver anytime decision making during execution. Heuristics are...

The problem considered in the paper is the joint learning and planning or Reinforcement Learning (RL) problem for Partially Observable Markov Decision Processes (POMDP) with unknown rewards and dynamics. We formulate an episodic learning problem with partial state knowledge. We then adapt UCRL and PSRL into heuristics for this episodic POMDP-RL problem in several ways and apply these heuristics...

Both materialization and backward-chaining as different modes of performing inference have complementary advantages and disadvantages. Materialization enables very efficient responses at query time, but at the cost of an expensive up front closure computation, which needs to be redone every time the knowledge base changes. Backward-chaining does not need such an expensive and change-sensitive p...

OBJECTIVES The aim of this article was to test a simple approach of using pixel density values from fluoroscopy images to enable gated radiotherapy. METHODS Anterior and lateral (LAT) from images were acquired from 18 patients referred for radical radiotherapy for non-small cell lung cancer for a period of 30-45 s. The amplitude of movement and the number of breathing cycles were determined i...

Abstract Model predictive control (MPC) is a powerful trajectory optimization technique capable of controlling complex nonlinear systems while respecting system constraints and ensuring safe operation. The MPC’s capabilities come at the cost high online computational complexity, requirement an accurate model dynamics, necessity tuning its parameters to specific application. main tunable paramet...

Filamentous cyanobacterium Fremyella diplosiphon is known to alter its pigmentation and morphology during complementary chromatic acclimation (CCA) to efficiently harvest available radiant energy for photosynthesis. F. diplosiphon cells are rectangular and filaments are longer under green light (GL), whereas smaller, spherical cells and short filaments are prevalent under red light (RL). Light ...