"When the world is destroyed, it will be destroyed not by its madmen but by the sanity of its experts and the superior ignorance of its bureaucrats." Decades before the advent of the Internet, Fernando António Nogueira Pessoa assumed a variety of identities with the ease that has become common in cyber-social platforms--those where cyber technologies play a part in human activity (for example, online banking, and social networks). Pessoa, a Portuguese poet, writer, literary critic, translator, publisher, and philosopher, wrote under his own name as well as 75 imaginary identities. He would write poetry or prose using one identity, then criticize that writing using another identity, then defend the original writing using yet another identity. Described by author Carmela Ciuraru as "the loving ringmaster, director, and traffic cop of his literary crew," Pessoa is one of the foremost Portuguese poets and a contributor to the Western canon. The story of Pessoa illustrates a key insight that holds true for the cyber-social systems of today: Identity costs little in the way of minting, forming, and maintaining yet demands a high price for its timely and accurate attribution to physical agency. Along with the low cost of minting and maintaining identities, a lack of constraints on using identities is a primary factor that facilitates adversarial innovations that rely on deception. With these factors in mind, we study the following problem: Will it be possible to engineer a decentralized system that can enforce honest usage of identity via mutual challenges and costly consequences when challenges fail? The success of such an approach will remedy currently deteriorating situations without requiring new infrastructure. For example, such a system should be able to reduce fake persons in social engineering attacks, malware that mimics the attributes of trusted software, and Sybil attacks that use fake identities to penetrate ad hoc networks. Note that many cyber-physical facilities--those where a physical mechanism is controlled or monitored by computer algorithms and tied closely to the internet and its users (for example, autonomous cars, medical monitoring)--also aim to enable users to remain anonymous and carry out certain tasks with only a persistent but pseudonymous identity. This form of short-term identity (especially in the networks that are ad hoc, hastily formed, and short lived) can remain uncoupled from a user's physical identity and allow them to maintain a strong form of privacy control.

The next challenge of game AI lies in Real Time Strategy (RTS) games. RTS games provide partially observable gaming environments, where agents interact with one another in an action space much larger than that of GO. Mastering RTS games requires both strong macro strategies and delicate micro level execution. Recently, great progress has been made in micro level execution, while complete solutions for macro strategies are still lacking. In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games. Trained by the Hierarchical Macro Strategy model, agents explicitly make macro strategy decisions and further guide their micro level execution. Moreover, each of the agents makes independent strategy decisions, while simultaneously communicating with the allies through leveraging a novel imitated cross-agent communication mechanism. We perform comprehensive evaluations on a popular 5v5 Multiplayer Online Battle Arena (MOBA) game. Our 5-AI team achieves a 48% winning rate against human player teams which are ranked top 1% in the player ranking system.

Recent successes of value-based multi-agent deep reinforcement learning employ optimism by limiting underestimation updates of value function estimator, through carefully controlled learning rate (Omidshafiei et al., 2017) or reduced update probability (Palmer et al., 2018). To achieve full cooperation when learning independently, an agent must estimate the state values contingent on having optimal teammates; therefore, value overestimation is frequency injected to counteract negative effects caused by unobservable teammate sub-optimal policies and explorations. Aiming to solve this issue through automatic scheduling, this paper introduces a decentralized quantile estimator, which we found empirically to be more stable, sample efficient and more likely to converge to the joint optimal policy.

Inferring the laws of interaction between particles and agents in complex dynamical systems from observational data is a fundamental challenge in a wide variety of disciplines. We propose a non-parametric statistical learning approach to estimate the governing laws of distance-based interactions, with no reference or assumption about their analytical form, from data consisting trajectories of interacting agents. We demonstrate the effectiveness of our learning approach both by providing theoretical guarantees, and by testing the approach on a variety of prototypical systems in various disciplines. These systems include homogeneous and heterogeneous agents systems, ranging from particle systems in fundamental physics to agent-based systems modeling opinion dynamics under the social influence, prey-predator dynamics, flocking and swarming, and phototaxis in cell dynamics.

The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of information between tasks, and the reuse of skills. We focus on one aspect in particular, namely the ability to generalise to unseen tasks. Parametric generalisation relies on the interpolation power of a function approximator that is given the task description as input; one of its most common form are universal value function approximators (UVFAs). Another way to generalise to new tasks is to exploit structure in the RL problem itself. Generalised policy improvement (GPI) combines solutions of previous tasks into a policy for the unseen task; this relies on instantaneous policy evaluation of old policies under the new reward function, which is made possible through successor features (SFs). Our proposed universal successor features approximators (USFAs) combine the advantages of all of these, namely the scalability of UVFAs, the instant inference of SFs, and the strong generalisation of GPI. We discuss the challenges involved in training a USFA, its generalisation properties and demonstrate its practical benefits and transfer abilities on a large-scale domain in which the agent has to navigate in a first-person perspective three-dimensional environment.

Continual learning is the ability of agents to improve their capacities throughout multiple tasks continually. While recent works in the literature of continual learning mostly focused on developing either particular loss functions or specialized structures of neural network explaining the episodic memory or neural plasticity, we study continual learning from the perspective of the training mechanism. Specifically, we propose a COnitnual Match BAsed Training (COMBAT) framework for training a population of advantage-actor-critic (A2C) agents in Pommerman, a partially observable multi-agent environment with no communication. Following the COMBAT framework, we trained an agent, namely, Navocado, that won the title of the top 1 learning agent in the NeurIPS 2018 Pommerman Competition. Two critical features of our agent are worth mentioning. Firstly, our agent did not learn from any demonstrations. Secondly, our agent is highly reproducible. As a technical report, we articulate the design of state space, action space, reward, and most importantly, the COMBAT framework for our Pommerman agent. We show in the experiments that Pommerman is a perfect environment for studying continual learning, and the agent can improve its performance by continually learning new skills without forgetting the old ones. Finally, the result in the Pommerman Competition verifies the robustness of our agent when competing with various opponents.

As computational power has continued to increase, and sensors have become more accurate, the corresponding advent of systems that are at once cognitive and immersive has arrived. These \textit{cognitive and immersive systems} (CAISs) fall squarely into the intersection of AI with HCI/HRI: such systems interact with and assist the human agents that enter them, in no small part because such systems are infused with AI able to understand and reason about these humans and their knowledge, beliefs, goals, communications, plans, etc. We herein explain our approach to engineering CAISs. We emphasize the capacity of a CAIS to develop and reason over a `theory of the mind' of its human partners. This capacity entails that the AI in question has a sophisticated model of the beliefs, knowledge, goals, desires, emotions, etc.\ of these humans. To accomplish this engineering, a formal framework of very high expressivity is needed. In our case, this framework is a \textit{cognitive event calculus}, a particular kind of quantified multi-operator modal logic, and a matching high-expressivity automated reasoner and planner. To explain, advance, and to a degree validate our approach, we show that a calculus of this type satisfies a set of formal requirements, and can enable a CAIS to understand a psychologically tricky scenario couched in what we call the \textit{cognitive polysolid framework} (CPF). We also formally show that a room that satisfies these requirements can have a useful property we term \emph{expectation of usefulness}. CPF, a sub-class of \textit{cognitive microworlds}, includes machinery able to represent and plan over not merely blocks and actions (such as seen in the primitive `blocks worlds' of old), but also over agents and their mental attitudes about both other agents and inanimate objects.

We introduce a new semantics for a logic of explicit and implicit beliefs based on the concept of multi-agent belief base. Differently from existing Kripke-style semantics for epistemic logic in which the notions of possible world and doxastic/epistemic alternative are primitive, in our semantics they are non-primitive but are defined from the concept of belief base. We provide a complete axiomatization and prove decidability for our logic via a finite model argument. We also provide a polynomial embedding of our logic into Fagin & Halpern's logic of general awareness and establish a complexity result for our logic via the embedding.

The recently released AlphaZero algorithm achieves superhuman performance in the games of chess, shogi and Go, which raises two open questions. Firstly, as there is a finite number of possibilities in the game, is there a quantifiable intelligence measurement for evaluating intelligent systems, e.g. AlphaZero? Secondly, AlphaZero introduces sophisticated reinforcement learning and self-play to efficiently encode the possible states, is there a simple information-theoretic model to represent the learning process and offer more insights in fostering strong AI systems? This paper explores the above two questions by proposing a simple variance of Shannon's communication model, the concept of intelligence entropy and the Unified Intelligence-Communication Model is proposed, which provide an information-theoretic metric for investigating the intelligence level and also provide an bound for intelligent agents in the form of Shannon's capacity, namely, the intelligence capacity. This paper then applies the concept and model to AlphaZero as a case study and explains the learning process of intelligent agent as turbo-like iterative decoding, so that the learning performance of AlphaZero may be quantitatively evaluated. Finally, conclusions are provided along with theoretical and practical remarks.

The rise of deep learning has brought artificial intelligence (AI) to the forefront. The ultimate goal of AI is to realize machines with human mind and consciousness, but existing achievements mainly simulate intelligent behavior on computer platforms. These achievements all belong to weak AI rather than strong AI. How to achieve strong AI is not known yet in the field of intelligence science. Currently, this field is calling for a new paradigm, especially Theory of Cognitive Relativity (TCR). The TCR aims to summarize a simple and elegant set of first principles about the nature of intelligence, at least including the Principle of World's Relativity and the Principle of Symbol's Relativity. The Principle of World's Relativity states that the subjective world an intelligent agent can observe is strongly constrained by the way it perceives the objective world. The Principle of Symbol's Relativity states that an intelligent agent can use any physical symbol system to describe what it observes in its subjective world. The two principles are derived from scientific facts and life experience. Thought experiments show that they are important to understand high-level intelligence and necessary to establish a scientific theory of mind and consciousness. Rather than brain-like intelligence, the TCR indeed advocates a promising change in direction to realize true AI, i.e. artificial general intelligence or artificial consciousness, particularly different from humans' and animals'. Furthermore, a TCR creed has been presented and extended to reveal the secrets of consciousness and to guide realization of conscious machines. In the sense that true AI could be diversely implemented in a brain-different way, the TCR would probably drive an intelligence revolution in combination with some additional first principles.