Explainable Artificial Intelligence (XAI), i.e., the development of more transparent and interpretable AI models, has gained increased traction over the last few years. This is due to the fact that, in conjunction with their growth into powerful and ubiquitous tools, AI models exhibit one detrimential characteristic: a performance-transparency trade-off. This describes the fact that the more complex a model's inner workings, the less clear it is how its predictions or decisions were achieved. But, especially considering Machine Learning (ML) methods like Reinforcement Learning (RL) where the system learns autonomously, the necessity to understand the underlying reasoning for their decisions becomes apparent. Since, to the best of our knowledge, there exists no single work offering an overview of Explainable Reinforcement Learning (XRL) methods, this survey attempts to address this gap. We give a short summary of the problem, a definition of important terms, and offer a classification and assessment of current XRL methods. We found that a) the majority of XRL methods function by mimicking and simplifying a complex model instead of designing an inherently simple one, and b) XRL (and XAI) methods often neglect to consider the human side of the equation, not taking into account research from related fields like psychology or philosophy. Thus, an interdisciplinary effort is needed to adapt the generated explanations to a (non-expert) human user in order to effectively progress in the field of XRL and XAI in general.

Recently, Dr. Ben Goertzel, CEO of SingularityNET convened the "COVID-19 Summit" to bring veterans in AI and Data Science researchers with epidemiologists, front-line doctors, and policymakers to look at how we handled the situation so far and what are the expectations going forward. One of the main themes from this Summit was the need for complex systems models such as agent-based models to inform policy. During this pandemic, at times, every policymaker around the world felt they were going into this pandemic without the information that they needed, even though we've dealt with other outbreaks such as SARS, MERS, etc.. The combined power of artificial intelligence and agent-based models in a Complex Adaptive System can give policymakers eyes, ears, and additional intelligence that can add transparency to the decision making process. Due to the technical nature of this topic, Dr. Deborah Duong, Director for AI Development at Rejuve and Director of Network Analytics at SingularityNET, gave a talk to explain the power of agent-based models combined with artificial intelligence, its usage, and the information it can provide policymakers and practical professionals in the field.

We consider a fair division setting where indivisible items are allocated to agents. Each agent in the setting has strictly negative, zero or strictly positive utility for each item. We, thus, make a distinction between items that are good for some agents and bad for other agents (i.e. mixed), good for everyone (i.e. goods) or bad for everyone (i.e. bads). For this model, we study axiomatic concepts of allocations such as jealousy-freeness up to one item, envy-freeness up to one item and Pareto-optimality. We obtain many new possibility and impossibility results in regard to combinations of these properties. We also investigate new computational tasks related to such combinations. Thus, we advance the state-of-the-art in fair division of mixed manna.

Artificial Intelligence (AI) is being increasingly used to develop systems that produce intelligent solutions. However, there is a major concern that whether the systems built will be trusted by humans. In order to establish trust in AI systems, there is a need for the user to understand the reasoning behind their solutions and therefore, the system should be able to explain and justify its output. In this paper, we use argumentation to provide explanations in the domain of AI planning. We present argument schemes to create arguments that explain a plan and its components; and a set of critical questions that allow interaction between the arguments and enable the user to obtain further information regarding the key elements of the plan. Finally, we present some properties of the plan arguments.

I survey recent progress on a classic and challenging problem in social choice: the fair division of indivisible items. I discuss how a computational perspective has provided interesting insights into and understanding of how to divide items fairly and efficiently. This has involved bringing to bear tools such as those used in knowledge representation, computational complexity, approximation methods, game theory, online analysis and communication complexity

Gravitational Search Algorithm (GSA) and Particle Swarm Optimization (PSO) are nature-inspired, swarm-based optimization algorithms respectively. Though they have been widely used for single-objective optimization since their inception, they suffer from premature convergence. Even though the hybrids of GSA and PSO perform much better, the problem remains. Hence, to solve this issue we have proposed a fuzzy mutation model for two hybrid versions of PSO and GSA - Gravitational Particle Swarm (GPS) and PSOGSA. The developed algorithms are called Mutation based GPS (MGPS) and Mutation based PSOGSA (MPSOGSA). The mutation operator is based on a fuzzy model where the probability of mutation has been calculated based on the closeness of particle to population centroid and improvement in the particle value. We have evaluated these two new algorithms on 23 benchmark functions of three categories (unimodal, multi-modal and multi-modal with fixed dimension). The experimental outcome shows that our proposed model outperforms their corresponding ancestors, MGPS outperforms GPS 13 out of 23 times (56.52%) and MPSOGSA outperforms PSOGSA 17 times out of 23 (73.91 %). We have also compared our results against those of recent optimization algorithms such as Sine Cosine Algorithm (SCA), Opposition-Based SCA, and Volleyball Premier League Algorithm (VPL). In addition, we have applied our proposed algorithms on some classic engineering design problems and the outcomes are satisfactory. The related codes of the proposed algorithms can be found in this link: Fuzzy-Mutation-Embedded-Hybrids-of-GSA-and-PSO.

Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e.g. pedestrians and vehicles) and road context information (e.g. lanes, traffic lights). This paper introduces VectorNet, a hierarchical graph neural network that first exploits the spatial locality of individual road components represented by vectors and then models the high-order interactions among all components. In contrast to most recent approaches, which render trajectories of moving agents and road context information as bird-eye images and encode them with convolutional neural networks (ConvNets), our approach operates on a vector representation. By operating on the vectorized high definition (HD) maps and agent trajectories, we avoid lossy rendering and computationally intensive ConvNet encoding steps. To further boost VectorNet's capability in learning context features, we propose a novel auxiliary task to recover the randomly masked out map entities and agent trajectories based on their context. We evaluate VectorNet on our in-house behavior prediction benchmark and the recently released Argoverse forecasting dataset. Our method achieves on par or better performance than the competitive rendering approach on both benchmarks while saving over 70% of the model parameters with an order of magnitude reduction in FLOPs. It also outperforms the state of the art on the Argoverse dataset.

In the future we can expect that artificial intelligent agents, once deployed, will be required to learn continually from their experience during their operational lifetime. Such agents will also need to communicate with humans and other agents regarding the content of their experience, in the context of passing along their learnings, for the purpose of explaining their actions in specific circumstances or simply to relate more naturally to humans concerning experiences the agent acquires that are not necessarily related to their assigned tasks. We argue that to support these goals, an agent would benefit from an episodic memory; that is, a memory that encodes the agent's experience in such a way that the agent can relive the experience, communicate about it and use its past experience, inclusive of the agents own past actions, to learn more effective models and policies. In this short paper, we propose one potential approach to provide an AI agent with such capabilities. We draw upon the ever-growing body of work examining the function and operation of the Medial Temporal Lobe (MTL) in mammals to guide us in adding an episodic memory capability to an AI agent composed of artificial neural networks (ANNs). Based on that, we highlight important aspects to be considered in the memory organization and we propose an architecture combining ANNs and standard Computer Science techniques for supporting storage and retrieval of episodic memories. Despite being initial work, we hope this short paper can spark discussions around the creation of intelligent agents with memory or, at least, provide a different point of view on the subject.

Theory of Mind is commonly defined as the ability to attribute mental states (e.g., beliefs, goals) to oneself, and to others. A large body of previous work - from the social sciences to artificial intelligence - has observed that Theory of Mind capabilities are central to providing an explanation to another agent or when explaining that agent's behaviour. In this paper, we build and expand upon previous work by providing an account of explanation in terms of the beliefs of agents and the mechanism by which agents revise their beliefs given possible explanations. We further identify a set of desiderata for explanations that utilize Theory of Mind. These desiderata inform our belief-based account of explanation.

Functional decision theory (FDT) is a fairly new mode of decision theory and a normative viewpoint on how an agent should maximize expected utility. The current standard in decision theory and computer science is causal decision theory (CDT), largely seen as superior to the main alternative evidential decision theory (EDT). These theories prescribe three distinct methods for maximizing utility. We explore how FDT differs from CDT and EDT, and what implications it has on the behavior of FDT agents and humans. It has been shown in previous research how FDT can outperform CDT and EDT. We additionally show FDT performing well on more classical game theory problems and argue for its extension to human problems to show that its potential for superiority is robust. We also make FDT more concrete by displaying it in an evolutionary environment, competing directly against other theories.