This document describes Pilot, our submission for Human-Agent Negotiation Challenge at IJCAI 2020. Pilot is a virtual human that participates in a sequence of three negotiations with a human partner. Our system is based on the Interactive Arbitration Guide Online (IAGO) negotiation framework. We leverage prior Affective Computing and Psychology research in negotiations to guide various key principles that define the behavior and personality of our agent. Pilot has been selected as one of the finalists for presentation at IJCAI.

This work addresses distributed optimization, where a network of agents wants to minimize a global strongly convex objective function. The global function can be written as a sum of local convex functions, each of which is associated with an agent. We propose a continuous-time distributed mirror descent algorithm that uses purely local information to converge to the global optimum. Unlike previous work on distributed mirror descent, we incorporate an integral feedback in the update, allowing the algorithm to converge with a constant step-size when discretized. We establish the asymptotic convergence of the algorithm using Lyapunov stability analysis. We further illustrate numerical experiments that verify the advantage of adopting integral feedback for improving the convergence rate of distributed mirror descent.

In sequential machine teaching, a teacher's objective is to provide the optimal sequence of inputs to sequential learners in order to guide them towards the best model. In this paper we extend this setting from current static one-data-set analyses to learners which change their learning algorithm or latent state to improve during learning, and to generalize to new datasets. We introduce a multi-agent formulation in which learners' inner state may change with the teaching interaction, which affects the learning performance in future tasks. In order to teach such learners, we propose an optimal control approach that takes the future performance of the learner after teaching into account. This provides tools for modelling learners having inner states, and machine teaching of meta-learning algorithms. Furthermore, we distinguish manipulative teaching, which can be done by effectively hiding data and also used for indoctrination, from more general education which aims to help the learner become better at generalization and learning in new datasets in the absence of a teacher.

During the first step of practical reasoning, i.e. deliberation or goals selection, an intelligent agent generates a set of pursuable goals and then selects which of them he commits to achieve. Explainable Artificial Intelligence (XAI) systems, including intelligent agents, must be able to explain their internal decisions. In the context of goals selection, agents should be able to explain the reasoning path that leads them to select (or not) a certain goal. In this article, we use an argumentation-based approach for generating explanations about that reasoning path. Besides, we aim to enrich the explanations with information about emerging conflicts during the selection process and how such conflicts were resolved. We propose two types of explanations: the partial one and the complete one and a set of explanatory schemes to generate pseudo-natural explanations. Finally, we apply our proposal to the cleaner world scenario.

An intelligent agent may in general pursue multiple procedural goals simultaneously, which may lead to arise some conflicts (incompatibilities) among them. In this paper, we focus on the incompatibilities that emerge due to resources limitations. Thus, the contribution of this article is twofold. On one hand, we give an algorithm for identifying resource incompatibilities from a set of pursued goals and, on the other hand, we propose two ways for selecting those goals that will continue to be pursued: (i) the first is based on abstract argumentation theory, and (ii) the second based on two algorithms developed by us. We illustrate our proposal using examples throughout the article.

This paper presents a novel online framework for safe crowd-robot interaction based on risk-sensitive stochastic optimal control, wherein the risk is modeled by the entropic risk measure. The sampling-based model predictive control relies on mode insertion gradient optimization for this risk measure as well as Trajectron++, a state-of-the-art generative model that produces multimodal probabilistic trajectory forecasts for multiple interacting agents. Our modular approach decouples the crowd-robot interaction into learning-based prediction and model-based control, which is advantageous compared to end-to-end policy learning methods in that it allows the robot's desired behavior to be specified at run time. In particular, we show that the robot exhibits diverse interaction behavior by varying the risk sensitivity parameter. A simulation study and a real-world experiment show that the proposed online framework can accomplish safe and efficient navigation while avoiding collisions with more than 50 humans in the scene.

This article is about an intelligent system to support ideas management as a result of a multi-agent system used in a distributed system with heterogeneous information as ideas and knowledge, after the results about an ontology to describe the meaning of these ideas. The intelligent system assists participants of the creativity workshop to manage their ideas and consequently proposing an ontology dedicated to ideas. During the creative workshop many creative activities and collaborative creative methods are used by roles immersed in this creativity workshop event where they share knowledge. The collaboration of these roles is physically distant, their interactions might be synchrony or asynchrony, and the information of the ideas are heterogeneous, so we can say that the process is distributed. Those ideas are writing in natural language by participants which have a role and the ideas are heterogeneous since some of them are described by schema, text or scenario of use. This paper presents first, our MAS and second our Ontology design.

The US Department of Defense (DoD) is to pit real-world fighters controlled by human pilots against aircraft flown by artificial intelligence in 2024, US Secretary of Defense Mark Esper said at the DOD Artificial Intelligence Symposium and Exposition. Speaking at the event, Esper said: "As an example of the tectonic impact of machine learning on the future of warfighting, the Defense Advanced Research Projects Agency (DARPA) recently conducted its third and final F-16 combat simulation between an AI-controlled system and an experienced Air Force fighter pilot." The real-world dogfights will be the culmination of work by DARPA which recently saw an AI-controlled F-16 beat an experienced US Air Force (USAF) pilot in a series of simulated dogfights. Esper added: "The AI agent's resounding victory demonstrated the ability of advanced algorithms to out-perform humans in virtual dogfights. In DARPA's AlphaDogfight, an AI built by Heron Systems beat a human F-16 pilot 5-0 following a number of AI vs AI simulated dogfights. AlphaDogfight was conducted as part of DARPA's Air Combat Evolution (ACE) designed to increase trust in combat autonomy, and demonstrate the utility of AI and autonomous systems as the US envisions a future where crewed aircraft are supported autonomous systems. Explaining ACE, DARPA said: "In a future air domain contested by adversaries, a single human pilot can increase lethality by effectively orchestrating multiple autonomous unmanned platforms from within a manned aircraft.

Prisoner's Dilemma mainly treat the choice to cooperate or defect as an atomic action. We propose to study online learning algorithm behavior in the Iterated Prisoner's Dilemma (IPD) game, where we explored the full spectrum of reinforcement learning agents: multi-armed bandits, contextual bandits and reinforcement learning. We have evaluate them based on a tournament of iterated prisoner's dilemma where multiple agents can compete in a sequential fashion. This allows us to analyze the dynamics of policies learned by multiple self-interested independent reward-driven agents, and also allows us study the capacity of these algorithms to fit the human behaviors. Results suggest that considering the current situation to make decision is the worst in this kind of social dilemma game. Multiples discoveries on online learning behaviors and clinical validations are stated.

We introduce multi-goal multi agent path finding (MAPF$^{MG}$) which generalizes the standard discrete multi-agent path finding (MAPF) problem. While the task in MAPF is to navigate agents in an undirected graph from their starting vertices to one individual goal vertex per agent, MAPF$^{MG}$ assigns each agent multiple goal vertices and the task is to visit each of them at least once. Solving MAPF$^{MG}$ not only requires finding collision free paths for individual agents but also determining the order of visiting agent's goal vertices so that common objectives like the sum-of-costs are optimized. We suggest two novel algorithms using different paradigms to address MAPF$^{MG}$: a heuristic search-based search algorithm called Hamiltonian-CBS (HCBS) and a compilation-based algorithm built using the SMT paradigm, called SMT-Hamiltonian-CBS (SMT-HCBS). Experimental comparison suggests limitations of compilation-based approach.