Game theory is a field of mathematics that is used to analyse the strategies used by decision makers in competitive situations. It can apply to humans, animals, and computers in various situations but is commonly used in AI research to study "multi-agent" environments where there is more than one system, for example several household robots cooperating to clean the house. Traditionally, the evolutionary dynamics of multi-agent systems have been analysed using simple, symmetric games, such as the classic Prisoner's Dilemma, where each player has access to the same set of actions. Although these games can provide useful insights into how multi-agent systems work and tell us how to achieve a desirable outcome for all players - known as the Nash equilibrium - they cannot model all situations. Our new technique allows us to quickly and easily identify the strategies used to find the Nash equilibrium in more complex asymmetric games - characterised as games where each player has different strategies, goals and rewards.

This paper proposes an agent with particle swarm optimization (PSO) based on a Fuzzy Markup Language (FML) for students learning performance evaluation and educational applications, and the proposed agent is according to the response data from a conventional test and an item response theory. First, we apply a GS-based parameter estimation mechanism to estimate the items parameters according to the response data, and then to compare its results with those of an IRT-based Bayesian parameter estimation mechanism. In addition, we propose a static-IRT test assembly mechanism to assemble a form for the conventional test. The presented FML-based dynamic assessment mechanism infers the probability of making a correct response to the item for a student with various abilities. Moreover, this paper also proposes a novel PFML learning mechanism for optimizing the parameters between items and students. Finally, we adopt a K-fold cross validation mechanism to evaluate the performance of the proposed agent. Experimental results show that the novel PFML learning mechanism for the parameter estimation and learning optimization performs favorably. We believe the proposed PFML will be a reference for education research and pedagogy and an important co-learning mechanism for future human-machine educational applications.

Across moral and non-moral domains, humans improve their expertise by learning from personal experience, by learning from being told, and by observing the outcomes when others face similar decisions. Children start with little experience and a small number of simple rules they have been taught by parents and teachers. Over time, they accumulate a richer and more nuanced understanding of when particular actions are right or wrong. The complexity of the world suggests the only way to acquire adequately complex decision criteria is through learning. Robots, however, are manufactured artifacts, whose computational state can be stored, copied, and retrieved. Even if mature moral and ethical expertise can only be created through experience and observation, it is conceivable this expertise can then be copied from one robot to another sufficiently similar one, unlike what is possible for humans.

"Reweighting rewards in embodied evolution to achieve a balanced distribution of labour," in Proceedings of the 14th European Conference on Artificial Life ECAL 2017 (Cambridge, MA: MIT Press), 44–51.

Can I have an AI and two blockchains? That's a joke but people tend to confuse or misuse the terms. There is undoubtedly a hype around these terms. In this post we are going to talk about AI (Artificial Intelligence), what it is and whether it is able to achieve what it is promising. We are going to do this, while going through the cases presented at the AI Congress 2018.

Asynchronous stochastic approximations are an important class of model-free algorithms that are readily applicable to multi-agent reinforcement learning (RL) and distributed control applications. When the system size is large, the aforementioned algorithms are used in conjunction with function approximations. In this paper, we present a complete analysis, including stability (almost sure boundedness) and convergence, of asynchronous stochastic approximations with asymptotically bounded biased errors, under easily verifiable sufficient conditions. As an application, we analyze the Policy Gradient algorithms and the more general Value Iteration based algorithms with noise. These are popular reinforcement learning algorithms due to their simplicity and effectiveness. Specifically, we analyze the asynchronous approximate counterpart of policy gradient (A2PG) and value iteration (A2VI) schemes. It is shown that the stability of these algorithms remains unaffected when the approximation errors are guaranteed to be asymptotically bounded, although possibly biased. Regarding convergence of A2VI, it is shown to converge to a fixed point of the perturbed Bellman operator when balanced step-sizes are used. Further, a relationship between these fixed points and the approximation errors is established. A similar analysis for A2PG is also presented.

Abstract-- We propose a reliable intersection control mechanism for strategic autonomous and connected vehicles (agents) in non-cooperative environments. Each agent has access to his/her earliest possible and desired passing times, and reports a passing time to the intersection manager, who allocates the intersection temporally to the agents in a First-Come- First-Serve basis. However, the agents might have conflicting interests and can take actions strategically. To this end, we analyze the strategic behaviors of the agents and formulate Nash equilibria for all possible scenarios. Furthermore, among all Nash equilibria we identify a socially optimal equilibrium that leads to a fair intersection allocation, and correspondingly we describe a strategy-proof intersection mechanism, which achieves reliable intersection control such that the strategic agents do not have any incentive to misreport their passing times strategically. I. INTRODUCTION Instead of classical yet inefficient traffic lighting systems, a First-Come-First-Serve (FCFS) based autonomous intersection control, which utilizes the connectivity of the autonomous agents with each other and the infrastructure, e.g., an intersection manager, has been introduced in [1].

Much of the day-to-day work of UX design focuses on optimizing manual, paper-based processes through the use of technology. Consider Amazon's origins, for example. Buying a book from a catalog has been around since 1498 when Aldus Manutius published a catalog of the books he printed. Almost 500 years later, Amazon put their catalog online and created a virtual, online experience for people to buy books. In Amazon's early years, this focus led to innovative steps in traditional transaction-based human–computer interaction (HCI).

Breakthroughs in technology are typically attributed to a single lone genius, but research led by DeepMind scientist Thore Graepel suggests the full power of AI will be unleashed through a collective approach of multi-agents. The UCL machine learning professor helped create AlphaGo, which pursued an individual strategy called competitive self-play to become the first computer program to defeat a human professional Go player in 2015. He's since turned his focus from competition to cooperation, using deep reinforcement learning to understand how teamwork develops among self-interested agents, whether they're computer programmes or human social dilemmas. "We believe that this kind of model is a powerful baseline to study these kinds of social dilemmas in more detail," said Graepel at the AI for Social Good symposium at the Turing Institute. His work forms part of DeepMind's ambitious mission "to solve intelligence".

Theory of mind (ToM; Premack & Woodruff, 1978) broadly refers to humans' ability to represent the mental states of others, including their desires, beliefs, and intentions. We propose to train a machine to build such models too. We design a Theory of Mind neural network -- a ToMnet -- which uses meta-learning to build models of the agents it encounters, from observations of their behaviour alone. Through this process, it acquires a strong prior model for agents' behaviour, as well as the ability to bootstrap to richer predictions about agents' characteristics and mental states using only a small number of behavioural observations. We apply the ToMnet to agents behaving in simple gridworld environments, showing that it learns to model random, algorithmic, and deep reinforcement learning agents from varied populations, and that it passes classic ToM tasks such as the "Sally-Anne" test (Wimmer & Perner, 1983; Baron-Cohen et al., 1985) of recognising that others can hold false beliefs about the world. We argue that this system -- which autonomously learns how to model other agents in its world -- is an important step forward for developing multi-agent AI systems, for building intermediating technology for machine-human interaction, and for advancing the progress on interpretable AI.