Knowledge and expertise in the real-world can be disjointedly owned. To solve a complex question, collaboration among experts is often called for. In this paper, we propose CollabQA, a novel QA task in which several expert agents coordinated by a moderator work together to answer questions that cannot be answered with any single agent alone. We make a synthetic dataset of a large knowledge graph that can be distributed to experts. We define the process to form a complex question from ground truth reasoning path, neural network agent models that can learn to solve the task, and evaluation metrics to check the performance. We show that the problem can be challenging without introducing prior of the collaboration structure, unless experts are perfect and uniform. Based on this experience, we elaborate extensions needed to approach collaboration tasks in real-world settings.

In online advertising, search engines sell ad placements for keywords continuously through auctions. This problem can be seen as an infinitely repeated game since the auction is executed whenever a user performs a query with the keyword. As advertisers may frequently change their bids, the game will have a large set of equilibria with potentially complex strategies. In this paper, we propose the use of natural strategies for reasoning in such setting as they are processable by artificial agents with limited memory and/or computational power as well as understandable by human users. To reach this goal, we introduce a quantitative version of Strategy Logic with natural strategies in the setting of imperfect information. In a first step, we show how to model strategies for repeated keyword auctions and take advantage of the model for proving properties evaluating this game. In a second step, we study the logic in relation to the distinguishing power, expressivity, and model-checking complexity for strategies with and without recall.

Realistic fine-grained multi-agent simulation of real-world complex systems is crucial for many downstream tasks such as reinforcement learning. Recent work has used generative models (GANs in particular) for providing high-fidelity simulation of real-world systems. However, such generative models are often monolithic and miss out on modeling the interaction in multi-agent systems. In this work, we take a first step towards building multiple interacting generative models (GANs) that reflects the interaction in real world. We build and analyze a hierarchical set-up where a higher-level GAN is conditioned on the output of multiple lower-level GANs. We present a technique of using feedback from the higher-level GAN to improve performance of lower-level GANs. We mathematically characterize the conditions under which our technique is impactful, including understanding the transfer learning nature of our set-up. We present three distinct experiments on synthetic data, time series data, and image domain, revealing the wide applicability of our technique.

It is widely acknowledged that transparency of automated decision making is crucial for deployability of intelligent systems, and explaining the reasons why some decisions are "good" and some are not is a way to achieving this transparency. We consider two variants of decision making, where "good" decisions amount to alternatives (i) meeting "most" goals, and (ii) meeting "most preferred" goals. We then define, for each variant and notion of "goodness" (corresponding to a number of existing notions in the literature), explanations in two formats, for justifying the selection of an alternative to audiences with differing needs and competences: lean explanations, in terms of goals satisfied and, for some notions of "goodness", alternative decisions, and argumentative explanations, reflecting the decision process leading to the selection, while corresponding to the lean explanations. To define argumentative explanations, we use assumption-based argumentation (ABA), a well-known form of structured argumentation. Specifically, we define ABA frameworks such that "good" decisions are admissible ABA arguments and draw argumentative explanations from dispute trees sanctioning this admissibility. Finally, we instantiate our overall framework for explainable decision-making to accommodate connections between goals and decisions in terms of decision graphs incorporating defeasible and non-defeasible information.

The evolution of the traditional call center into an omnichannel contact center has allowed companies to view the function less as a cost driver and more as an opportunity to provide strategic, experience-oriented customer care. With customers engaged via SMS, websites, chats, and social media, identifying customers' reasons for initiating contact has become a core analytics use case for virtually any contact-center operation. This increased focus on customer care requires today's leaders to manage more data than ever before--and as more transactions migrate from in-person channels, data management becomes even more important to the customer experience. But many businesses still struggle to capture and process customers' voice conversations. Across industries, these interactions represent the majority of all incoming volume, and projections suggest that these calls aren't going away anytime soon.

The quality of learning generally improves with the scale and diversity of data. Companies and institutions can therefore benefit from building models over shared data. Many cloud and blockchain platforms, as well as government initiatives, are interested in providing this type of service. These cooperative efforts face a challenge, which we call ``exclusivity attacks''. A firm can share distorted data, so that it learns the best model fit, but is also able to mislead others. We study protocols for long-term interactions and their vulnerability to these attacks, in particular for regression and clustering tasks. We conclude that the choice of protocol, as well as the number of Sybil identities an attacker may control, is material to vulnerability.

Recent advances in reinforcement learning (RL) have increased complexity which, especially for deep RL, has brought forth challenges related to explainability [1]. The opacity of state-of-the-art RL algorithms has led to model developers having a limited understanding of their agents' policies and no influence over learned strategies [2]. While concerns surrounding explainability have been noted for AI in general, it is only more recently that attempts have been made to explain RL systems [3, 1, 4, 5]. These attempts have resulted in a wide suite of methods requiring various degrees of expert knowledge, either about the state-action domain or about the specific RL algorithm. Further, they typically rely on post-hoc analysis of learned policies which give only observational assurances of agents' behaviour. We instead propose an intrinsic method of regularizing agents' actions based on a given prior. While current methods for RL regularization aim to improve training performance - e.g., by maximizing the entropy of the action distribution [6], or by minimising the distance to a prior sub-optimal state-action distribution [7] - our aim is the characterization of our agents' behaviours. We also extend the current regularization techniques to accommodate multi-agent systems which allows intrinsic characterization of individual agents. We provide a formal argument for the rationale of our method and demonstrate its efficacy in a toy problem where agents learn to navigate to a destination on a grid by performing, e.g., only right turns (under the premise that right turns are

Intelligent physical systems as embodied cognitive systems must perform high-level reasoning while concurrently managing an underlying control architecture. The link between cognition and control must manage the problem of converting continuous values from the real world to symbolic representations (and back). To generate effective behaviors, reasoning must include a capacity to replan, acquire and update new information, detect and respond to anomalies, and perform various operations on system goals. But, these processes are not independent and need further exploration. This paper examines an agent's choices when multiple goal operations co-occur and interact, and it establishes a method of choosing between them. We demonstrate the benefits and discuss the trade offs involved with this and show positive results in a dynamic marine search task.

A pair of researchers from the University of Montreal today published a pre-print research paper on creating "more intelligent artificial agents" by imitating the human brain. We've heard that one before, but this time's a little different. The big idea here is all about giving artificial intelligence agents more agency. Despite the progress made in social neuroscience and in developmental psychology, only in the last decade, serious efforts have started focusing on the neural mechanisms of social interaction, which were seen as the "dark matter" of social neuroscience. Basically, there's something other than just algorithms and architecture that makes our brains tick.

Information sharing is key in building team cognition and enables coordination and cooperation. High-performing human teams also benefit from acting strategically with hierarchical levels of iterated communication and rationalizability, meaning a human agent can reason about the actions of their teammates in their decision-making. Yet, the majority of prior work in Multi-Agent Reinforcement Learning (MARL) does not support iterated rationalizability and only encourage inter-agent communication, resulting in a suboptimal equilibrium cooperation strategy. In this work, we show that reformulating an agent's policy to be conditional on the policies of its neighboring teammates inherently maximizes Mutual Information (MI) lower-bound when optimizing under Policy Gradient (PG). Building on the idea of decision-making under bounded rationality and cognitive hierarchy theory, we show that our modified PG approach not only maximizes local agent rewards but also implicitly reasons about MI between agents without the need for any explicit ad-hoc regularization terms. Our approach, InfoPG, outperforms baselines in learning emergent collaborative behaviors and sets the state-of-the-art in decentralized cooperative MARL tasks. Our experiments validate the utility of InfoPG by achieving higher sample efficiency and significantly larger cumulative reward in several complex cooperative multi-agent domains.