Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning.

Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which they fail. In this work, we empirically investigate the learning power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial problems that arise in the multi-agent setting, such as an exponential number of joint actions or the lack of an explicit coordination mechanism. Our results extend those in Castellini et al. (Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS'19.International Foundation for Autonomous Agents and Multiagent Systems, pp 1862-1864, 2019) and quantify how well various approaches can represent the requisite value functions, and help us identify the reasons that can impede good performance, like sparsity of the values or too tight coordination requirements.

A deep learning approach to identify unhealthy advertisements in street view images.

While outdoor advertisements are common features within towns and cities, they may reinforce social inequalities in health. Vulnerable populations in deprived areas may have greater exposure to fast food, gambling and alcohol advertisements, which may encourage their consumption. Understanding who is exposed and evaluating potential policy restrictions requires a substantial manual data collection effort. To address this problem we develop a deep learning workflow to automatically extract and classify unhealthy advertisements from street-level images. We introduce the Liverpool [Formula: see text] Street View (LIV360SV) dataset for evaluating our workflow. The dataset contains 25,349, 360 degree, street-level images collected via cycling with a GoPro Fusion camera, recorded Jan 14th-18th 2020. 10,106 advertisements were identified and classified as food (1335), alcohol (217), gambling (149) and other (8405). We find evidence of social inequalities with a larger proportion of food advertisements located within deprived areas and those frequented by students. Our project presents a novel implementation for the incidental classification of street view images for identifying unhealthy advertisements, providing a means through which to identify areas that can benefit from tougher advertisement restriction policies for tackling social inequalities.

Bayesian optimisation of restriction zones for bluetongue control.

We investigate the restriction of animal movements as a method to control the spread of bluetongue, an infectious disease of livestock that is becoming increasingly prevalent due to the onset of climate change. We derive control policies for the UK that minimise the number of infected farms during an outbreak using Bayesian optimisation and a simulation-based model of BT. Two cases are presented: first, where the region of introduction is randomly selected from England and Wales to find a generalised strategy. This "national" model is shown to be just as effective at subduing the spread of bluetongue as the current strategy of the UK government. Our proposed controls are simpler to implement, affect fewer farms in the process and, in so doing, minimise the potential economic implications. Second, we consider policies that are tailored to the specific region in which the first infection was detected. Seven different regions in the UK were explored and improvements in efficiency from the use of specialised policies presented. As a consequence of the increasing temperatures associated with climate change, efficient control measures for vector-borne diseases such as this are expected to become increasingly important. Our work demonstrates the potential value of using Bayesian optimisation in developing cost-effective disease management strategies.

Symmetric Decomposition of Asymmetric Games.

We introduce new theoretical insights into two-population asymmetric games allowing for an elegant symmetric decomposition into two single population symmetric games. Specifically, we show how an asymmetric bimatrix game (A,B) can be decomposed into its symmetric counterparts by envisioning and investigating the payoff tables (A and B) that constitute the asymmetric game, as two independent, single population, symmetric games. We reveal several surprising formal relationships between an asymmetric two-population game and its symmetric single population counterparts, which facilitate a convenient analysis of the original asymmetric game due to the dimensionality reduction of the decomposition. The main finding reveals that if (x,y) is a Nash equilibrium of an asymmetric game (A,B), this implies that y is a Nash equilibrium of the symmetric counterpart game determined by payoff table A, and x is a Nash equilibrium of the symmetric counterpart game determined by payoff table B. Also the reverse holds and combinations of Nash equilibria of the counterpart games form Nash equilibria of the asymmetric game. We illustrate how these formal relationships aid in identifying and analysing the Nash structure of asymmetric games, by examining the evolutionary dynamics of the simpler counterpart games in several canonical examples.

Space Debris Removal: Learning to Cooperate and the Price of Anarchy.

In this paper we study space debris removal from a game-theoretic perspective. In particular we focus on the question whether and how self-interested agents can cooperate in this dilemma, which resembles a tragedy of the commons scenario. We compare centralised and decentralised solutions and the corresponding price of anarchy, which measures the extent to which competition approximates cooperation. In addition we investigate whether agents can learn optimal strategies by reinforcement learning. To this end, we improve on an existing high fidelity orbital simulator, and use this simulator to obtain a computationally efficient surrogate model that can be used for our subsequent game-theoretic analysis. We study both single- and multi-agent approaches using stochastic (Markov) games and reinforcement learning. The main finding is that the cost of a decentralised, competitive solution can be significant, which should be taken into consideration when forming debris removal strategies.