Yasaman Khazaeni

Yasaman Khazaeni, Christos G. Cassandras

In previous work, a Cooperative Receding Horizon (CRH) controller was developed for solving cooperative multi-agent problems in uncertain environments. In this paper, we overcome several limitations of this controller, including potential instabilities in the agent trajectories and poor performance due to inaccurate estimation of a reward-to-go function. We propose an event-driven CRH controller to solve the maximum reward collection problem (MRCP) where multiple agents cooperate to maximize the total reward collected from a set of stationary targets in a given mission space. Rewards are non-increasing functions of time and the environment is uncertain with new targets detected by agents at random time instants. The controller sequentially solves optimization problems over a planning horizon and executes the control for a shorter action horizon, where both are defined by certain events associated with new information becoming available. In contrast to the earlier CRH controller, we reduce the originally infinite-dimensional feasible control set to a finite set at each time step. We prove some properties of this new controller and include simulation results showing its improved performance compared to the original one.

Yasaman Khazaeni, Christos G. Cassandras

We consider event-driven methods in a general framework for the control and optimization of multi-agent systems, viewing them as stochastic hybrid systems. Such systems often have feasible realizations in which the events needed to excite an on-line event-driven controller cannot occur, rendering the use of such controllers ineffective. We show that this commonly happens in environments which contain discrete points of interest which the agents must visit. To address this problem in event-driven gradient-based optimization problems, we propose a new metric for the objective function which creates a potential field guaranteeing that gradient values are non-zero when no events are present and which results in eventual event excitation. We apply this approach to the class of cooperative multi-agent data collection problems using the event-driven Infinitesimal Perturbation Analysis (IPA) methodology and include numerical examples illustrating its effectiveness.

Sarath Sreedharan, Tathagata Chakraborti, Yara Rizk et al.

A new design of an AI assistant that has become increasingly popular is that of an "aggregated assistant" -- realized as an orchestrated composition of several individual skills or agents that can each perform atomic tasks. In this paper, we will talk about the role of planning in the automated composition of such assistants and explore how concepts in automated planning can help to establish transparency of the inner workings of the assistant to the end-user.

Sohini Upadhyay, Mikhail Yurochkin, Mayank Agarwal et al.

We formulate a new problem at the intersectionof semi-supervised learning and contextual bandits,motivated by several applications including clini-cal trials and ad recommendations. We demonstratehow Graph Convolutional Network (GCN), a semi-supervised learning approach, can be adjusted tothe new problem formulation. We also propose avariant of the linear contextual bandit with semi-supervised missing rewards imputation. We thentake the best of both approaches to develop multi-GCN embedded contextual bandit. Our algorithmsare verified on several real world datasets.

Djallel Bouneffouf, Raphaël Féraud, Sohini Upadhyay et al.

In this paper, we analyze and extend an online learning framework known as Context-Attentive Bandit, motivated by various practical applications, from medical diagnosis to dialog systems, where due to observation costs only a small subset of a potentially large number of context variables can be observed at each iteration;however, the agent has a freedom to choose which variables to observe. We derive a novel algorithm, called Context-Attentive Thompson Sampling (CATS), which builds upon the Linear Thompson Sampling approach, adapting it to Context-Attentive Bandit setting. We provide a theoretical regret analysis and an extensive empirical evaluation demonstrating advantages of the proposed approach over several baseline methods on a variety of real-life datasets

Tathagata Chakraborti, Vatche Isahagian, Rania Khalaf et al.

In this survey, we study how recent advances in machine intelligence are disrupting the world of business processes. Over the last decade, there has been steady progress towards the automation of business processes under the umbrella of ``robotic process automation'' (RPA). However, we are currently at an inflection point in this evolution, as a new paradigm called ``Intelligent Process Automation'' (IPA) emerges, bringing machine learning (ML) and artificial intelligence (AI) technologies to bear in order to improve business process outcomes. The purpose of this paper is to provide a survey of this emerging theme and identify key open research challenges at the intersection of AI and business processes. We hope that this emerging theme will spark engaging conversations at the RPA Forum.

Yara Rizk, Vatche Isahagian, Scott Boag et al.

Robotic process automation (RPA) has emerged as the leading approach to automate tasks in business processes. Moving away from back-end automation, RPA automated the mouse-click on user interfaces; this outside-in approach reduced the overhead of updating legacy software. However, its many shortcomings, namely its lack of accessibility to business users, have prevented its widespread adoption in highly regulated industries. In this work, we explore interactive automation in the form of a conversational digital assistant. It allows business users to interact with and customize their automation solutions through natural language. The framework, which creates such assistants, relies on a multi-agent orchestration model and conversational wrappers for autonomous agents including RPAs. We demonstrate the effectiveness of our proposed approach on a loan approval business process and a travel preapproval business process.

Djallel Bouneffouf, Sohini Upadhyay, Yasaman Khazaeni

We consider a novel variant of the contextual bandit problem (i.e., the multi-armed bandit with side-information, or context, available to a decision-maker) where the reward associated with each context-based decision may not always be observed("missing rewards"). This new problem is motivated by certain online settings including clinical trial and ad recommendation applications. In order to address the missing rewards setting, we propose to combine the standard contextual bandit approach with an unsupervised learning mechanism such as clustering. Unlike standard contextual bandit methods, by leveraging clustering to estimate missing reward, we are able to learn from each incoming event, even those with missing rewards. Promising empirical results are obtained on several real-life datasets.

Salomón Wollenstein-Betech, Christian Muise, Christos G. Cassandras et al.

Usage of automated controllers which make decisions on an environment are widespread and are often based on black-box models. We use Knowledge Compilation theory to bring explainability to the controller's decision given the state of the system. For this, we use simulated historical state-action data as input and build a compact and structured representation which relates states with actions. We implement this method in a Traffic Light Control scenario where the controller selects the light cycle by observing the presence (or absence) of vehicles in different regions of the incoming roads.

Yara Rizk, Vatche Isahagian, Merve Unuvar et al.

The ubiquity of smart phones and electronic devices has placed a wealth of information at the fingertips of consumers as well as creators of digital content. This has led to millions of notifications being issued each second from alerts about posted YouTube videos to tweets, emails and personal messages. Adding work related notifications and we can see how quickly the number of notifications increases. Not only does this cause reduced productivity and concentration but has also been shown to cause alert fatigue. This condition makes users desensitized to notifications, causing them to ignore or miss important alerts. Depending on what domain users work in, the cost of missing a notification can vary from a mere inconvenience to life and death. Therefore, in this work, we propose an alert and notification framework that intelligently issues, suppresses and aggregates notifications, based on event severity, user preferences, or schedules, to minimize the need for users to ignore, or snooze their notifications and potentially forget about addressing important ones. Our framework can be deployed as a backend service, but is better suited to be integrated into proactive conversational agents, a field receiving a lot of attention with the digital transformation era, email services, news services and others. However, the main challenge lies in developing the right machine learning algorithms that can learn models from a wide set of users while customizing these models to individual users' preferences.

Hongyi Wang, Mikhail Yurochkin, Yuekai Sun et al.

Federated learning allows edge devices to collaboratively learn a shared model while keeping the training data on device, decoupling the ability to do model training from the need to store the data in the cloud. We propose Federated matched averaging (FedMA) algorithm designed for federated learning of modern neural network architectures e.g. convolutional neural networks (CNNs) and LSTMs. FedMA constructs the shared global model in a layer-wise manner by matching and averaging hidden elements (i.e. channels for convolution layers; hidden states for LSTM; neurons for fully connected layers) with similar feature extraction signatures. Our experiments indicate that FedMA not only outperforms popular state-of-the-art federated learning algorithms on deep CNN and LSTM architectures trained on real world datasets, but also reduces the overall communication burden.

Tathagata Chakraborti, Yasaman Khazaeni

This paper builds upon recent work in the declarative design of dialogue agents and proposes an exciting new tool -- D3BA -- Declarative Design for Digital Business Automation, built to optimize business processes using the power of AI planning. The tool provides a powerful framework to build, optimize, and maintain complex business processes and optimize them by composing with services that automate one or more subtasks. We illustrate salient features of this composition technique, compare with other philosophies of composition, and highlight exciting opportunities for research in this emerging field of business process automation.

Yara Rizk, Abhishek Bhandwalder, Scott Boag et al.

Business process automation is a booming multi-billion-dollar industry that promises to remove menial tasks from workers' plates -- through the introduction of autonomous agents -- and free up their time and brain power for more creative and engaging tasks. However, an essential component to the successful deployment of such autonomous agents is the ability of business users to monitor their performance and customize their execution. A simple and user-friendly interface with a low learning curve is necessary to increase the adoption of such agents in banking, insurance, retail and other domains. As a result, proactive chatbots will play a crucial role in the business automation space. Not only can they respond to users' queries and perform actions on their behalf but also initiate communication with the users to inform them of the system's behavior. This will provide business users a natural language interface to interact with, monitor and control autonomous agents. In this work, we present a multi-agent orchestration framework to develop such proactive chatbots by discussing the types of skills that can be composed into agents and how to orchestrate these agents. Two use cases on a travel preapproval business process and a loan application business process are adopted to qualitatively analyze the proposed framework based on four criteria: performance, coding overhead, scalability, and agent overlap.

Sohini Upadhyay, Mayank Agarwal, Djallel Bounneffouf et al.

Building multi-domain AI agents is a challenging task and an open problem in the area of AI. Within the domain of dialog, the ability to orchestrate multiple independently trained dialog agents, or skills, to create a unified system is of particular significance. In this work, we study the task of online posterior dialog orchestration, where we define posterior orchestration as the task of selecting a subset of skills which most appropriately answer a user input using features extracted from both the user input and the individual skills. To account for the various costs associated with extracting skill features, we consider online posterior orchestration under a skill execution budget. We formalize this setting as Context Attentive Bandit with Observations (CABO), a variant of context attentive bandits, and evaluate it on simulated non-conversational and proprietary conversational datasets.

Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh et al.

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled through our framework. We then develop an inference approach that allows us to synthesize a more expressive global network without additional supervision, data pooling and with as few as a single communication round. We then demonstrate the efficacy of our approach on federated learning problems simulated from two popular image classification datasets.

Yasaman Khazaeni, Christos G. Cassandras

We propose a new event-driven method for on-line trajectory optimization to solve the data harvesting problem: in a two-dimensional mission space, N mobile agents are tasked with the collection of data generated at M stationary sources and delivery to a base with the goal of minimizing expected collection and delivery delays. We define a new performance measure that addresses the event excitation problem in event-driven controllers and formulate an optimal control problem. The solution of this problem provides some insights on its structure, but it is computationally intractable, especially in the case where the data generating processes are stochastic. We propose an agent trajectory parameterization in terms of general function families which can be subsequently optimized on line through the use of Infinitesimal Perturbation Analysis (IPA). Properties of the solutions are identified, including robustness with respect to the stochastic data generation process and scalability in the size of the event set characterizing the underlying hybrid dynamical system. Explicit results are provided for the case of elliptical and Fourier series trajectories and comparisons with a state-of-the-art graph-based algorithm are given.

Yasaman Khazaeni, Christos G. Cassandras

We propose a new method for trajectory planning to solve the data harvesting problem. In a two-dimensional mission space, $N$ mobile agents are tasked with the collection of data generated at $M$ stationary sources and delivery to a base aiming at minimizing expected delays. An optimal control formulation of this problem provides some initial insights regarding its solution, but it is computationally intractable, especially in the case where the data generating processes are stochastic. We propose an agent trajectory parameterization in terms of general function families which can be subsequently optimized on line through the use of Infinitesimal Perturbation Analysis (IPA). Explicit results are provided for the case of elliptical and Fourier series trajectories and some properties of the solution are identified, including robustness with respect to the data generation processes and scalability in the size of an event set characterizing the underlying hybrid dynamic system.