In this paper, we investigate the concentration properties of cumulative rewards in Markov Decision Processes (MDPs), focusing on both asymptotic and non-asymptotic settings. We introduce a unified approach to characterize reward concentration in MDPs, covering both infinite-horizon settings (i.e., average and discounted reward frameworks) and finite-horizon setting. Our asymptotic results include the law of large numbers, the central limit theorem, and the law of iterated logarithms, while our non-asymptotic bounds include Azuma-Hoeffding-type inequalities and a non-asymptotic version of the law of iterated logarithms. Additionally, we explore two key implications of our results. First, we analyze the sample path behavior of the difference in rewards between any two stationary policies. Second, we show that two alternative definitions of regret for learning policies proposed in the literature are rate-equivalent. Our proof techniques rely on a novel martingale decomposition of cumulative rewards, properties of the solution to the policy evaluation fixed-point equation, and both asymptotic and non-asymptotic concentration results for martingale difference sequences.

We study a general class of entropy-regularized multi-variate LQG mean field games (MFGs) in continuous time with $K$ distinct sub-population of agents. We extend the notion of actions to action distributions (exploratory actions), and explicitly derive the optimal action distributions for individual agents in the limiting MFG. We demonstrate that the optimal set of action distributions yields an $\epsilon$-Nash equilibrium for the finite-population entropy-regularized MFG. Furthermore, we compare the resulting solutions with those of classical LQG MFGs and establish the equivalence of their existence.

Patrice Caine, the chairman and CEO of Thales Group, discusses his company's artificial intelligence strategy, market applications and sustained research and development investment with Defense & Aerospace Report Editor Vago Muradian. Thales sponsored reporters' travel to the company's cortAIx AI research facility in Montreal, Canada.

Artificial intelligence is the future of aerospace and defence, but the chief executive of French giant Thales says there is one application of the technology that his firm will never pursue: autonomous killing machines. "It has been discussed for too long, to be honest. It's not that difficult to say no to killer robots," Patrice Caine told a group of journalists in Montreal Thursday. AI-powered lethal weapons aren't the sort of thing that most CEOs have to worry about, but Thales operates in the aerospace, transportation and defence sectors, and Caine told the Financial Post that he imagines AI will be embedded in just about every aspect of the company's business in the next five years or so. "I would say you will find some kind of AI almost everywhere," he said.

Urban Airship has raised $25 million in Series F funding. The company started out as a platform supporting push notifications, but has since expanded to include other marketing channels like email, SMS, mobile wallets and voice assistants. The goal is to be the platform managing messaging and unifying customer data across all these channels. Altogether, Urban Airship said it's now delivered more than two trillion messages, doubling the number from a year ago. Recent product additions include voice notifications on Amazon Alexa (which is still in beta testing) and automated in-app messaging. The company has signed up new enterprise customers like AMC, Magazine Luiza and Royal Automobile Club.

Cinematic, Ambient, Inhabitable Narrative Environments (CAINEs) are conceptual AI-driven interactive story systems combining text, audio, and visual imagery that are scalable and adaptable to a wide range of storytelling needs and interactor inputs. Conceived by at artist outside the AI community, they represent an opportunity to use AI in a nontraditional and immersive narrative fashion that relies not on the goal-based arrangement of story elements, but on the accretion and association of those elements in the minds of interactors. This paper represents the initial phase of the project’s development.