Industry has always been in the pursuit of becoming more economically efficient and the current focus has been to reduce human labour using modern technologies. Even with cutting edge technologies, which range from packaging robots to AI for fault detection, there is still some ambiguity on the aims of some new systems, namely, whether they are automated or autonomous. In this paper, we indicate the distinctions between automated and autonomous systems as well as review the current literature and identify the core challenges for creating learning mechanisms of autonomous agents. We discuss using different types of extended realities, such as digital twins, how to train reinforcement learning agents to learn specific tasks through generalisation. Once generalisation is achieved, we discuss how these can be used to develop self-learning agents. We then introduce self-play scenarios and how they can be used to teach self-learning agents through a supportive environment that focuses on how the agents can adapt to different environments. We introduce an initial prototype of our ideas by solving a multi-armed bandit problem using two ε-greedy algorithms. Further, we discuss future applications in the industrial management realm and propose a modular architecture for improving the decision-making process via autonomous agents.

No abstract

A common problem for deep reinforcement learning networks is a lack of training data to learn specific tasks through generalization. In this paper, we discuss using extended reality to train reinforcement learning agents to overcome this problem. We review popular reinforcement learning and extended reality techniques and then synthesize the information, this allowed us to develop our proposed design for a self learning agent. Meta learning offers an important way forward, but the agents ability to perform self-play is considered crucial for achieving successful AI. Therefore, we focus on improving self-play scenarios for teaching self-learning agents, by providing a supportive environment for improved agent-environment interaction.

Introduction:The gestation when small for gestational age (SGA) is first associated with asthma is not well understood. Here, we use routinely acquired data from 10 weeks gestation to up to 28 years of age to test the hypothesis that SGA before birth is associated with an increased risk for asthma in a large population born between 1987 and 2015.Methods: Databases were linked to produce a single database that held antenatal fetal ultrasound measurements; maternal characteristics; birth measurements; childhood anthropometric measurements at age 5 years; hospital admission data ; and family doctor prescribing (2009)(2010)(2011)(2012)(2013)(2014)(2015). Asthma admission and receipt of any asthma medications were the outcomes. Analyses related single and then multiple anthropometric measurements to asthma outcomes.Results: Outcome data were available for 63,930 individuals. Increased length in the first-trimester size was associated with a reduced odds ratio (OR) for asthma admission of 0.991 [0.983, 0.998] per mm increase and also a shorter time to first admission, with a hazard ratio risk of 0.987 [0.980, 0.994] per mm increase.Independent of all earlier measurements, increased height at 5 years (available in a subset of 15,760) was associated with reduced OR for an asthma admission, with OR of 0.874 [0.790, 0.967] per z score. Longitudinal measurements of weight were not related to asthma outcomes.Conclusions: Longer first-trimester length is associated with more favorable asthma outcomes, and subsequently, increased height in childhood is also independently associated with more favorable asthma outcomes. Interventions that reduce SGA and encourage healthy postnatal growth might improve asthma outcomes.

No abstract