Results 91 to 100 of about 120,210 (259)
Risk‐aware safe reinforcement learning for control of stochastic linear systems
Asian Journal of Control, EarlyView.Abstract This paper presents a risk‐aware safe reinforcement learning (RL) control design for stochastic discrete‐time linear systems. Rather than using a safety certifier to myopically intervene with the RL controller, a risk‐informed safe controller is also learned besides the RL controller, and the RL and safe controllers are combined together ...
Babak Esmaeili +2 more
wiley +1 more source
Efficacy, safety and cost‐effectiveness of CAR‐T therapy
British Journal of Clinical Pharmacology, EarlyView.CAR T‐cells demonstrate high efficacy in blood cancers, including ALL, MM and DLBCL. Innovations target solid tumours despite challenges such as antigen escape. Combination therapies enhance the delivery and infiltration of CAR T cells. Toxicity, cost and resistance remain major barriers to clinical use.
Emina Karahmet Sher +7 more
wiley +1 more source
Prioritizing Feasible and Impactful Actions to Enable Secure AI Development and Use in Biology
Biotechnology and Bioengineering, EarlyView.ABSTRACT As artificial intelligence continues to enhance biological innovation, the potential for misuse must be addressed to fully unlock the potential societal benefits. While significant work has been done to evaluate general‐purpose AI and specialized biological design tools (BDTs) for biothreat creation risks, actionable steps to mitigate the risk
Josh Dettman +4 more
wiley +1 more source
Business Strategy and the Environment, EarlyView.ABSTRACT The concept of predictive maintenance in advanced manufacturing systems is crucial from the point of view of resource efficiency in the era of high competitiveness forced by energy transformation in the digital economy. Against the backdrop of sustainability and the opportunities a data cooperative offers, the combination of predictive ...
Christian Schachtner +6 more
wiley +1 more source
Business Strategy and the Environment, EarlyView.ABSTRACT This article contributes to sustainability research by investigating the complex, geopolitically induced challenges faced by industrial supply chains under international sanctions. Using Iran's steel industry as a case, it examines sustainability barriers through the lens of stakeholder theory. A mixed methods approach was employed.
Seyed Hamed Moosavirad +2 more
wiley +1 more source
Business Strategy and the Environment, EarlyView.ABSTRACT As sustainability transitions accelerate, firms increasingly engage in innovation ecosystems to pursue disruptive sustainable innovation (DSI). Nevertheless, empirical understanding regarding how innovation ecosystem coopetition—simultaneous cooperation and competition among interdependent actors—translates into sustainability‐oriented ...
Jin‐Sup Jung, Min‐Jae Lee
wiley +1 more source
A hidden Markov model and reinforcement learning‐based strategy for fault‐tolerant control
The Canadian Journal of Chemical Engineering, EarlyView.Abstract This study introduces a data‐driven control strategy integrating hidden Markov models (HMM) and reinforcement learning (RL) to achieve resilient, fault‐tolerant operation against persistent disturbances in nonlinear chemical processes. Called hidden Markov model and reinforcement learning (HMMRL), this strategy is evaluated in two case studies
Tamera Leitao +2 more
wiley +1 more source
Logarithmic Regret Bounds for Continuous-Time Average-Reward Markov Decision Processes
SIAM Journal on Control and OptimizationWe consider reinforcement learning for continuous-time Markov decision processes (MDPs) in the infinite-horizon, average-reward setting. In contrast to discrete-time MDPs, a continuous-time process moves to a state and stays there for a random holding time after an action is taken.
Gao, Xuefeng, Zhou, Xun Yu
openaire +3 more sources
Q-learning with Nearest Neighbors
, 2018 We consider model-free reinforcement learning for infinite-horizon discounted Markov Decision Processes (MDPs) with a continuous state space and unknown transition kernel, when only a single sample path under an arbitrary policy of the system is ...
Shah, Devavrat, Xie, Qiaomin
core
Restricted Tweedie stochastic block models
Canadian Journal of Statistics, EarlyView.Abstract The stochastic block model (SBM) is a widely used framework for community detection in networks, where the network structure is typically represented by an adjacency matrix. However, conventional SBMs are not directly applicable to an adjacency matrix that consists of nonnegative zero‐inflated continuous edge weights.
Jie Jian, Mu Zhu, Peijun Sang
wiley +1 more source