Existing approaches for the design of interpretable agent behavior consider different measures of interpretability in isolation. In this paper we posit that, in the design and deployment of human-aware agents in the real world, notions of interpretability are just some among many considerations; and the techniques developed in isolation lack two key properties to be useful when considered together: they need to be able to 1) deal with their mutually competing properties; and 2) an open world where the human is not just there to interpret behavior in one specific form. To this end, we consider three well-known instances of interpretable behavior studied in existing literature -- namely, explicability, legibility, and predictability -- and propose a revised model where all these behaviors can be meaningfully modeled together. We will highlight interesting consequences of this unified model and motivate, through results of a user study, why this revision is necessary.

In this paper we present a deep learning framework for solving large-scale multiagent non-cooperative stochastic games using fictitious play. The Hamilton-Jacobi-Bellman (HJB) PDE associated with each agent is reformulated into a set of Forward-Backward Stochastic Differential Equations (FBSDEs) and solved via forward sampling on a suitably defined neural network architecture. Decision making in multi-agent systems suffers from curse of dimensionality and strategy degeneration as the number of agents and time horizon increase. We propose a novel Deep FBSDE controller framework which is shown to outperform the current state-of-the-art deep fictitious play algorithm on a high dimensional interbank lending/borrowing problem. More importantly, our approach mitigates the curse of many agents and reduces computational and memory complexity, allowing us to scale up to 1,000 agents in simulation, a scale which, to the best of our knowledge, represents a new state of the art. Stochastic differential games represent a framework for investigating scenarios where multiple players make decisions while operating in a dynamic and stochastic environment. A key step in the study of games is obtaining the Nash equilibrium among players (Osborne & Rubinstein, 1994). A Nash equilibrium represents the solution of non-cooperative game where two or more players are involved. Each player cannot gain benefit by modifying his/her own strategy given opponents equilibrium strategy.

For autonomous vehicles to safely share the road with human drivers, autonomous vehicles must abide by specific "road rules" that human drivers have agreed to follow. "Road rules" include rules that drivers are required to follow by law -- such as the requirement that vehicles stop at red lights -- as well as more subtle social rules -- such as the implicit designation of fast lanes on the highway. In this paper, we provide empirical evidence that suggests that -- instead of hard-coding road rules into self-driving algorithms -- a scalable alternative may be to design multi-agent environments in which road rules emerge as optimal solutions to the problem of maximizing traffic flow. We analyze what ingredients in driving environments cause the emergence of these road rules and find that two crucial factors are noisy perception and agents' spatial density. We provide qualitative and quantitative evidence of the emergence of seven social driving behaviors, ranging from obeying traffic signals to following lanes, all of which emerge from training agents to drive quickly to destinations without colliding. Our results add empirical support for the social road rules that countries worldwide have agreed on for safe, efficient driving.

This paper studies the problem of distributed classification with a network of heterogeneous agents. The agents seek to jointly identify the underlying target class that best describes a sequence of observations. The problem is first abstracted to a hypothesis-testing framework, where we assume that the agents seek to agree on the hypothesis (target class) that best matches the distribution of observations. Non-Bayesian social learning theory provides a framework that solves this problem in an efficient manner by allowing the agents to sequentially communicate and update their beliefs for each hypothesis over the network. Most existing approaches assume that agents have access to exact statistical models for each hypothesis. However, in many practical applications, agents learn the likelihood models based on limited data, which induces uncertainty in the likelihood function parameters. In this work, we build upon the concept of uncertain models to incorporate the agents' uncertainty in the likelihoods by identifying a broad set of parametric distribution that allows the agents' beliefs to converge to the same result as a centralized approach. Furthermore, we empirically explore extensions to non-parametric models to provide a generalized framework of uncertain models in non-Bayesian social learning.

Following decades of sustained improvement, metaheuristics are one of the great success stories of optimization research. However, in order for research in metaheuristics to avoid fragmentation and a lack of reproducibility, there is a pressing need for stronger scientific and computational infrastructure to support the development, analysis and comparison of new approaches. We argue that, via principled choice of infrastructure support, the field can pursue a higher level of scientific enquiry. We describe our vision and report on progress, showing how the adoption of common protocols for all metaheuristics can help liberate the potential of the field, easing the exploration of the design space of metaheuristics.

Humans have a rich representation of the entities in their environment. Entities are described by their attributes, and entities that share attributes are often semantically related. For example, if two books have "Natural Language Processing" as the value of their `title' attribute, we can expect that their `topic' attribute will also be equal, namely, "NLP". Humans tend to generalize such observations, and infer sufficient conditions under which the `topic' attribute of any entity is "NLP". If robots need to interact successfully with humans, they need to represent entities, attributes, and generalizations in a similar way. This ends in a contextualized cognitive agent that can adapt its understanding, where context provides sufficient conditions for a correct understanding. In this work, we address the problem of how to obtain these representations through human-robot interaction. We integrate visual perception and natural language input to incrementally build a semantic model of the world, and then use inductive reasoning to infer logical rules that capture generic semantic relations, true in this model. These relations can be used to enrich the human-robot interaction, to populate a knowledge base with inferred facts, or to remove uncertainty in the robot's sensory inputs.

In decentralized optimization, it is common algorithmic practice to have nodes interleave (local) gradient descent iterations with gossip (i.e. averaging over the network) steps. Motivated by the training of large-scale machine learning models, it is also increasingly common to require that messages be {\em lossy compressed} versions of the local parameters. In this paper, we show that, in such compressed decentralized optimization settings, there are benefits to having {\em multiple} gossip steps between subsequent gradient iterations, even when the cost of doing so is appropriately accounted for e.g. by means of reducing the precision of compressed information. In particular, we show that having $O(\log\frac{1}{\epsilon})$ gradient iterations {with constant step size} - and $O(\log\frac{1}{\epsilon})$ gossip steps between every pair of these iterations - enables convergence to within $\epsilon$ of the optimal value for smooth non-convex objectives satisfying Polyak-\L{}ojasiewicz condition. This result also holds for smooth strongly convex objectives. To our knowledge, this is the first work that derives convergence results for nonconvex optimization under arbitrary communication compression.

The broad applicability of artificial intelligence in today's society necessitates the need to develop and deploy technologies that can build trust in emerging areas, counter asymmetric threats, and adapt to the ever-changing needs of complex environments. As part of a new collaboration to advance and support AI research, the MIT Stephen A. Schwarzman College of Computing and the Defense Science and Technology Agency in Singapore are awarding funding to 13 projects led by researchers within the college that target one or more of the following themes: trustworthy AI, enhancing human cognition in complex environments, and AI for everyone. The 13 research projects selected are highlighted below. Emerging machine learning technology has the potential to significantly help with and even fully automate many tasks that have confidently been entrusted only to humans so far. Leveraging recent advances in realistic graphics rendering, data modeling, and inference, Madry's team is building a radically new toolbox to fuel streamlined development and deployment of trustworthy machine learning solutions.

The broad applicability of artificial intelligence in today's society necessitates the need to develop and deploy technologies that can build trust in emerging areas, counter asymmetric threats, and adapt to the ever-changing needs of complex environments. As part of a new collaboration to advance and support AI research, the MIT Stephen A. Schwarzman College of Computing and the Defense Science and Technology Agency in Singapore are awarding funding to 13 projects led by researchers within the college that target one or more of the following themes: trustworthy AI, enhancing human cognition in complex environments, and AI for everyone. The 13 research projects selected are highlighted below. Emerging machine learning technology has the potential to significantly help with and even fully automate many tasks that have confidently been entrusted only to humans so far. Leveraging recent advances in realistic graphics rendering, data modeling, and inference, Madry's team is building a radically new toolbox to fuel streamlined development and deployment of trustworthy machine learning solutions.

COVID-19 was declared a pandemic by the World Health Organization (WHO) on March 11th, 2020. With half of the world's countries in lockdown as of April due to this pandemic, monitoring and understanding the spread of the virus and infection rates and how these factors relate to behavioural and societal parameters is crucial for effective policy making. This paper aims to investigate the effectiveness of masks, social distancing, lockdown and self-isolation for reducing the spread of SARS-CoV-2 infections. Our findings based on agent-based simulation modelling show that whilst enforcing a lockdown is widely believed to be the most efficient method to quickly reduce infection numbers, the practice of social distancing and the usage of surgical masks can potentially be more effective than enforcing a lockdown. Our multivariate analysis of simulation results using the Morris Elementary Effects Method suggests that if a sufficient proportion of the population wore surgical masks and followed social distancing regulations, then SARS-CoV-2 infections can be controlled without enforcing a lockdown.