HOFLON automates process start-ups and grade-changes using offline RL and online optimization.
problem Manual operation of start-ups and grade-changes by experts is declining, leaving plant owners without the necessary tacit know-how.
method HOFLON combines offline RL to learn a latent manifold and long-horizon Q-critic, and online optimization to maximize Q-critic while penalizing deviations and excessive variable changes.
result HOFLON outperforms standard offline RL in industrial case studies, delivering better cumulative rewards than historical data.
We analyze the sectoral dynamics of startup venture financing. Based on a dataset of 52000 start-ups and 110000 funding rounds in the United States from 2000 to 2017, and by applying both Principal Component Analysis (PCA) and Tensor Component Analysis (TCA) in sector space, we visualize and measure the evolution of th…
Study compares ruin probabilities under independence vs. dependence assumptions.
problem Underestimation of ruin probability when claims are dependent.
method Copulas for claim dependence analysis, sensitivity analysis.
result Dependent claims lead to underestimation of ruin probability.
Paper uses deep reinforcement learning for better control of rocket engines during start-up phases.
problem Lack of optimal control during transient phases of liquid rocket engines.
method Deep reinforcement learning approach for optimal control of a gas-generator engine's continuous start-up phase.
result Deep reinforcement learning controller achieves highest performance and minimal computational effort.
Second-order estimator improves continuous-time policy evaluation.
problem Estimating value surfaces from discrete data with time-inhomogeneous dynamics.
method Moment-matching coefficients for high-order generator regression.
result Second-order estimator consistently outperforms Bellman baseline.
This paper introduces Deep Incremental Boosting, a new technique derived from AdaBoost, specifically adapted to work with Deep Learning methods, that reduces the required training time and improves generalisation. We draw inspiration from Transfer of Learning approaches to reduce the start-up time to training each incr…
We introduce mu-scalar curvature for a K"ahler metric with a moment map mu and start up a study on constant mu-scalar curvature K"ahler metric as a generalization of both cscK metric and K"ahler-Ricci soliton and as a continuity path to extremal metric. We study some fundamental constraints to the existence of constant…
Nanotechnology is the first major worldwide research initiative of the 21st century and probably is the solution vector in the economic environment. Also, innovation is widely recognized as a key factor in the economic development of nations, and is essential for the competitiveness of the industrial firms as well. Pol…
Study reveals which startup valuation factors are most critical.
problem Understanding the complex factors influencing startup valuations.
method Hierarchical prediction models using decision trees and random forests.
result Identifies which factors most significantly impact startup valuations.
Jointly tackles assortment and pricing in retail, using bandit models.
problem Maximizing revenue or profit in retail through optimal assortment and pricing.
method Contextual bandits with a flexible, interpretable model for high-dimensional contexts and actions.
result Proves lower regret compared to state-of-the-art methods in various bandit and pricing models.
We study ranking quantilized mean-field games to select top-performing agents.
problem Selecting top-performing agents in competitive scenarios.
method Developed two formulations: target-based and threshold-based, and provided analytic and semi-explicit solutions.
result Analytic and semi-explicit solutions for quantilized mean-field consistency conditions.