Collective behavior of people in large groups and emergent crowd dynamics can have dangerous and disastrous results when panic is introduced. These events can be caused by emergency situations such as fires in a large building or a stampeding effect when people are rushing in a densely packed area. In this paper, we will use an agent-based modeling approach to simulate different evacuation events in an attempt to understand what is the most efficient scenario. Specifically, we will focus on how people with disabilities are impacted by chosen parameters during an emergency evacuation. We chose an ABM to simulate this because we want to specify specific roles for different "agents" in our model. Specifically, we will focus on the influence of people with disabilities on crowd dynamics and the optimal exits. Does the placement of seating for people with disabilities affect the time it takes for the last person to exit the building? What effect does poor signage have on the time it takes for able-bodied and people with disabilities to exit safely? What happens if some people do not know about alternative exits in their panicked state? Using our agent-based model, we will investigate these questions while also adjusting other outside effects such as the density of the crowd, the speed at which people exit, and the location of people at the start of the simulation.

In heterogeneous networks (HetNets), the overlap of small cells and the macro cell causes severe cross-tier interference. Although there exist some approaches to address this problem, they usually require global channel state information, which is hard to obtain in practice, and get the sub-optimal power allocation policy with high computational complexity. To overcome these limitations, we propose a multi-agent deep reinforcement learning (MADRL) based power control scheme for the HetNet, where each access point makes power control decisions independently based on local information. To promote cooperation among agents, we develop a penalty-based Q learning (PQL) algorithm for MADRL systems. By introducing regularization terms in the loss function, each agent tends to choose an experienced action with high reward when revisiting a state, and thus the policy updating speed slows down. In this way, an agent's policy can be learned by other agents more easily, resulting in a more efficient collaboration process. Simulation results show that our proposed PQL can learn the desired power control policy from a dynamic environment where the locations of users change episodically and outperform existing DTE MADRL algorithms. The authors are with the Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, U.K. (e-mail: k.xu21@imperial.ac.uk; huynh.nguyen@imperial.ac.uk; geoffrey.li@imperial.ac.uk) In conventional cellular networks, a macro base station (BS) needs to provide access to the core network for all user devices (UDs) in the cell.

We propose an agent-based opinion formation model characterised by a two-fold novelty. First, we realistically assume that each agent cannot measure the opinion of its neighbours with infinite resolution and accuracy, and hence it can only classify the opinion of others as agreeing much more, or more, or comparably, or less, or much less (than itself) with a given statement. This leads to a classification-based rule for opinion update. Second, we consider three complementary agent traits suggested by significant sociological and psychological research: conformism, radicalism and stubbornness. We rely on World Values Survey data to show that the proposed model has the potential to predict the evolution of opinions in real life: the classification-based approach and complementary agent traits produce rich collective behaviours, such as polarisation, consensus, and clustering, which can yield predicted opinions similar to survey results.

We propose a hierarchical framework for collaborative intelligent systems. This framework organizes research challenges based on the nature of the collaborative activity and the information that must be shared, with each level building on capabilities provided by lower levels. We review research paradigms at each level, with a description of classical engineering-based approaches and modern alternatives based on machine learning, illustrated with a running example using a hypothetical personal service robot. We discuss cross-cutting issues that occur at all levels, focusing on the problem of communicating and sharing comprehension, the role of explanation and the social nature of collaboration. We conclude with a summary of research challenges and a discussion of the potential for economic and societal impact provided by technologies that enhance human abilities and empower people and society through collaboration with Intelligent Systems.

Privacy protection and nonconvexity are two challenging problems in decentralized optimization and learning involving sensitive data. Despite some recent advances addressing each of the two problems separately, no results have been reported that have theoretical guarantees on both privacy protection and saddle/maximum avoidance in decentralized nonconvex optimization. We propose a new algorithm for decentralized nonconvex optimization that can enable both rigorous differential privacy and saddle/maximum avoiding performance. The new algorithm allows the incorporation of persistent additive noise to enable rigorous differential privacy for data samples, gradients, and intermediate optimization variables without losing provable convergence, and thus circumventing the dilemma of trading accuracy for privacy in differential privacy design. More interestingly, the algorithm is theoretically proven to be able to efficiently { guarantee accuracy by avoiding} convergence to local maxima and saddle points, which has not been reported before in the literature on decentralized nonconvex optimization. The algorithm is efficient in both communication (it only shares one variable in each iteration) and computation (it is encryption-free), and hence is promising for large-scale nonconvex optimization and learning involving high-dimensional optimization parameters. Numerical experiments for both a decentralized estimation problem and an Independent Component Analysis (ICA) problem confirm the effectiveness of the proposed approach.

Adequate strategizing of agents behaviors is essential to solving cooperative MARL problems. One intuitively beneficial yet uncommon method in this domain is predicting agents future behaviors and planning accordingly. Leveraging this point, we propose a two-level hierarchical architecture that combines a novel information-theoretic objective with a trajectory prediction model to learn a strategy. To this end, we introduce a latent policy that learns two types of latent strategies: individual $z_A$, and relational $z_R$ using a modified Graph Attention Network module to extract interaction features. We encourage each agent to behave according to the strategy by conditioning its local $Q$ functions on $z_A$, and we further equip agents with a shared $Q$ function that conditions on $z_R$. Additionally, we introduce two regularizers to allow predicted trajectories to be accurate and rewarding. Empirical results on Google Research Football (GRF) and StarCraft (SC) II micromanagement tasks show that our method establishes a new state of the art being, to the best of our knowledge, the first MARL algorithm to solve all super hard SC II scenarios as well as the GRF full game with a win rate higher than $95\%$, thus outperforming all existing methods. Videos and brief overview of the methods and results are available at: https://sites.google.com/view/hier-strats-marl/home.

In this paper, we investigate the optimal robot path planning problem for high-level specifications described by co-safe linear temporal logic (LTL) formulae. We consider the scenario where the map geometry of the workspace is partially-known. Specifically, we assume that there are some unknown regions, for which the robot does not know their successor regions a priori unless it reaches these regions physically. In contrast to the standard game-based approach that optimizes the worst-case cost, in the paper, we propose to use regret as a new metric for planning in such a partially-known environment. The regret of a plan under a fixed but unknown environment is the difference between the actual cost incurred and the best-response cost the robot could have achieved if it realizes the actual environment with hindsight. We provide an effective algorithm for finding an optimal plan that satisfies the LTL specification while minimizing its regret. A case study on firefighting robots is provided to illustrate the proposed framework. We argue that the new metric is more suitable for the scenario of partially-known environment since it captures the trade-off between the actual cost spent and the potential benefit one may obtain for exploring an unknown region.

Traditional electrical power grids have long suffered from operational unreliability, instability, inflexibility, and inefficiency. Smart grids (or smart energy systems) continue to transform the energy sector with emerging technologies, renewable energy sources, and other trends. Artificial intelligence (AI) is being applied to smart energy systems to process massive and complex data in this sector and make smart and timely decisions. However, the lack of explainability and governability of AI is a major concern for stakeholders hindering a fast uptake of AI in the energy sector. This paper provides a review of AI explainability and governance in smart energy systems. We collect 3,568 relevant papers from the Scopus database, automatically discover 15 parameters or themes for AI governance in energy and elaborate the research landscape by reviewing over 150 papers and providing temporal progressions of the research. The methodology for discovering parameters or themes is based on "deep journalism", our data-driven deep learning-based big data analytics approach to automatically discover and analyse cross-sectional multi-perspective information to enable better decision-making and develop better instruments for governance. The findings show that research on AI explainability in energy systems is segmented and narrowly focussed on a few AI traits and energy system problems. This paper deepens our knowledge of AI governance in energy and is expected to help governments, industry, academics, energy prosumers, and other stakeholders to understand the landscape of AI in the energy sector, leading to better design, operations, utilisation, and risk management of energy systems.

Consider the relationship between a regulator (the principal) and a pharmaceutical company (the agent). The pharmaceutical company wishes to sell a product to make a profit, and the FDA wishes to ensure that only efficacious drugs are released to the public. The efficacy of the drug is not known to the FDA, so the pharmaceutical company must run a costly trial to prove efficacy to the FDA. Critically, the statistical protocol used to establish efficacy affects the behavior of a strategic, self-interested pharmaceutical company; a lower standard of statistical evidence incentivizes the pharmaceutical company to run more trials for drugs that are less likely to be effective, since the drug may pass the trial by chance, resulting in large profits. The interaction between the statistical protocol and the incentives of the pharmaceutical company is crucial to understanding this system and designing protocols with high social utility. In this work, we discuss how the principal and agent can enter into a contract with payoffs based on statistical evidence. When there is stronger evidence for the quality of the product, the principal allows the agent to make a larger profit. We show how to design contracts that are robust to an agent's strategic actions, and derive the optimal contract in the presence of strategic behavior.

In the field of derivative-free optimization, both of its main branches, the deterministic and nature-inspired techniques, experienced in recent years substantial advancement. In this paper, we provide an extensive computational comparison of selected methods from each of these branches. The chosen representatives were either standard and well-utilized methods, or the best-performing methods from recent numerical comparisons. The computational comparison was performed on five different benchmark sets and the results were analyzed in terms of performance, time complexity, and convergence properties of the selected methods. The results showed that, when dealing with situations where the objective function evaluations are relatively cheap, the nature-inspired methods have a significantly better performance than their deterministic counterparts. However, in situations when the function evaluations are costly or otherwise prohibited, the deterministic methods might provide more consistent and overall better results.