Latest in cs.ma

total 1961took 0.11s
Dynamics Concentration of Large-Scale Tightly-Connected NetworksMar 14 2019The ability to achieve coordinated behavior -- engineered or emergent -- on networked systems has attracted widespread interest over several fields. This has led to remarkable advances on the development of a theoretical understanding of the conditions ... More
Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation LearningMar 14 2019Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such behaviors arise ... More
CIMAX: Collective Information Maximization in Robotic Swarms Using Local CommunicationMar 13 2019Robotic swarms and mobile sensor networks are used for environmental monitoring in various domains and areas of operation. Especially in otherwise inaccessible environments decentralized robotic swarms can be advantageous due to their high spatial resolution ... More
Resource Abstraction for Reinforcement Learning in Multiagent Congestion ProblemsMar 13 2019Real-world congestion problems (e.g. traffic congestion) are typically very complex and large-scale. Multiagent reinforcement learning (MARL) is a promising candidate for dealing with this emerging complexity by providing an autonomous and distributed ... More
STRATA: A Unified Framework for Task Assignments in Large Teams of Heterogeneous RobotsMar 12 2019Large teams of robots have the potential to solve complex multi-task problems that are intractable for a single robot working independently. However, solving complex multi-task problems requires leveraging the relative strengths of different robots in ... More
Self-triggered distributed k-order coverage controlMar 12 2019A k-order coverage control problem is studied where a network of agents must deploy over a desired area. The objective is to deploy all the agents in a decentralized manner such that a certain coverage performance metric of the network is maximized. Unlike ... More
Imitation Learning of Factored Multi-agent Reactive ModelsMar 12 2019We apply recent advances in deep generative modeling to the task of imitation learning from biological agents. Specifically, we apply variations of the variational recurrent neural network model to a multi-agent setting where we learn policies of individual ... More
Reachability and Coverage Planning for Connected Agents: Extended VersionMar 11 2019Motivated by the increasing appeal of robots in information-gathering missions, we study multi-agent path planning problems in which the agents must remain interconnected. We model an area by a topological graph specifying the movement and the connectivity ... More
Blameworthiness in Multi-Agent SettingsMar 11 2019We provide a formal definition of blameworthiness in settings where multiple agents can collaborate to avoid a negative outcome. We first provide a method for ascribing blameworthiness to groups relative to an epistemic state (a distribution over causal ... More
On self-organised aggregation dynamics in swarms of robots with informed robotsMar 09 2019In this paper, we use simulated swarms of robots to further explore the aggregation dynamics generated by these simple individual mechanisms. Our objective is to study the introduction of "informed robots", and to study how many of these are needed to ... More
Minimizing Travel in the Uniform Dispersal Problem for Robotic SensorsMar 08 2019The limited energy capacity of individual robotic agents in a swarm often limits the possible cooperative tasks they can perform. In this work, we investigate the problem of covering an unknown connected grid environment (e.g. a maze or connected corridors) ... More
Learning Hierarchical Teaching in Cooperative Multiagent Reinforcement LearningMar 07 2019Heterogeneous knowledge naturally arises among different agents in cooperative multiagent reinforcement learning. As such, learning can be greatly improved if agents can effectively pass their knowledge on to other agents. Existing work has demonstrated ... More
Intelligent Knowledge Distribution: Constrained-Action POMDPs for Resource-Aware Multi-Agent CommunicationMar 07 2019This paper addresses a fundamental question of multi-agent knowledge distribution: what information should be sent to whom and when, with the limited resources available to each agent? Communication requirements for multi-agent systems can be rather high ... More
A Privacy-preserving Disaggregation Algorithm for Non-intrusive Management of Flexible EnergyMar 07 2019We consider a resource allocation problem involving a large number of agents with individual constraints subject to privacy, and a central operator whose objective is to optimizing a global, possibly non-convex, cost while satisfying the agents'c onstraints. ... More
Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum GamesMar 07 2019Learning in a multi-agent system is challenging because agents are simultaneously learning and the environment is not stationary, undermining convergence guarantees. To address this challenge, this paper presents a new gradient-based learning algorithm, ... More
Coping with Large Traffic Volumes in Schedule-Driven Traffic Signal ControlMar 06 2019Recent work in decentralized, schedule-driven traffic control has demonstrated the ability to significantly improve traffic flow efficiency in complex urban road networks. However, in situations where vehicle volumes increase to the point that the physical ... More
Softpressure: A Schedule-Driven Backpressure Algorithm for Coping with Network CongestionMar 06 2019We consider the problem of minimizing the delay of jobs moving through a directed graph of service nodes. In this problem, each node may have several links and is constrained to serve one link at a time. As jobs move through the network, they can pass ... More
Mean Field Equilibrium: Uniqueness, Existence, and Comparative StaticsMar 06 2019The standard solution concept for stochastic games is Markov perfect equilibrium (MPE); however, its computation becomes intractable as the number of players increases. Instead, we consider mean field equilibrium (MFE) that has been popularized in the ... More
Multi-Agent Learning in Network Zero-Sum Games is a Hamiltonian SystemMar 05 2019Zero-sum games are natural, if informal, analogues of closed physical systems where no energy/utility can enter or exit. This analogy can be extended even further if we consider zero-sum network (polymatrix) games where multiple agents interact in a closed ... More
Demonstration of a Time-Efficient Mobility System Using a Scaled Smart CityMar 05 2019The implementation of connected and automated vehicle (CAV) technologies enables a novel computational framework to deliver real-time control actions that optimize travel time, energy, and safety. Hardware is an integral part of any practical implementation ... More
A behavior driven approach for sampling rare event situations for autonomous vehiclesMar 04 2019Performance evaluation of urban autonomous vehicles requires a realistic model of the behavior of other road users in the environment. Learning such models from data involves collecting naturalistic data of real-world human behavior. In many cases, acquisition ... More
Modeling Social Group Communication with Multi-Agent Imitation LearningMar 04 2019In crowded social scenarios with a myriad of external stimuli, human brains exhibit a natural ability to filter out irrelevant information and narrowly focus their attention. In the midst of multiple groups of people, humans use such sensory gating to ... More
α-Rank: Multi-Agent Evaluation by EvolutionMar 04 2019Mar 12 2019We introduce {\alpha}-Rank, a principled evolutionary dynamics methodology for the evaluation and ranking of agents in large-scale multi-agent interactions, grounded in a novel dynamical game-theoretic solution concept called Markov-Conley chains (MCCs). ... More
α-Rank: Multi-Agent Evaluation by EvolutionMar 04 2019We introduce {\alpha}-Rank, a principled evolutionary dynamics methodology, for the evaluation and ranking of agents in large-scale multi-agent interactions, grounded in a novel dynamical game-theoretic solution concept called Markov-Conley chains (MCCs). ... More
Microscopic Traffic Simulation by Cooperative Multi-agent Deep Reinforcement LearningMar 04 2019Expert human drivers perform actions relying on traffic laws and their previous experience. While traffic laws are easily embedded into an artificial brain, modeling human complex behaviors which come from past experience is a more challenging task. One ... More
Attacking Power Indices by Manipulating Player ReliabilityMar 04 2019We investigate the manipulation of power indices in TU-cooperative games by stimulating (subject to a budget constraint) changes in the propensity of other players to participate to the game. We display several algorithms that show that the problem is ... More
Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent AgentsMar 02 2019The emergence of complex life on Earth is often attributed to the arms race that ensued from a huge number of organisms all competing for finite resources. We present an artificial intelligence research environment, inspired by the human game genre of ... More
Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence ResearchMar 02 2019Evolution has produced a multi-scale mosaic of interacting adaptive units. Innovations arise when perturbations push parts of the system away from stable equilibria into new regimes where previously well-adapted solutions no longer work. Here we explore ... More
A Cooperative Multi-Agent Reinforcement Learning Framework for Resource Balancing in Complex Logistics NetworkMar 02 2019Resource balancing within complex transportation networks is one of the most important problems in real logistics domain. Traditional solutions on these problems leverage combinatorial optimization with demand and supply forecasting. However, the high ... More
Trajectory convergence from coordinate-wise decrease of quadratic energy functions, and applications to platoonsMar 01 2019We consider trajectories where the sign of the derivative of each entry is opposite to that of the corresponding entry in the gradient of an energy function. We show that this condition guarantees convergence when the energy function is quadratic and ... More
Frictional Unemployment on Labor Flow NetworksMar 01 2019We develop an alternative theory to the aggregate matching function in which workers search for jobs through a network of firms: the labor flow network. The lack of an edge between two companies indicates the impossibility of labor flows between them ... More
Egocentric Bias and Doubt in Cognitive AgentsMar 01 2019Modeling social interactions based on individual behavior has always been an area of interest, but prior literature generally presumes rational behavior. Thus, such models may miss out on capturing the effects of biases humans are susceptible to. This ... More
Evaluation Mechanism of Collective Intelligence for Heterogeneous Agents GroupMar 01 2019Collective intelligence is manifested when multiple agents coherently work in observation, interaction, decision-making and action. In this paper, we define and quantify the intelligence level of heterogeneous agents group with the improved Anytime Universal ... More
Infer Your Enemies and Know Yourself, Learning in Real-Time Bidding with Partially Observable OpponentsFeb 28 2019Real-time bidding, as one of the most popular mechanisms for selling online ad slots, facilitates advertisers to reach their potential customers. The goal of bidding optimization is to maximize the advertisers' return on investment (ROI) under a certain ... More
Mobile Formation Coordination and Tracking Control for Multiple Non-holonomic VehiclesFeb 28 2019This paper addresses forward motion control for trajectory tracking and mobile formation coordination for a group of non-holonomic vehicles on SE(2). Firstly, by constructing an intermediate attitude variable which involves vehicles' position information ... More
Achieving Non-Uniform Densities in Vibration Driven Robot Swarms Using Phase Separation TheoryFeb 27 2019In robot swarms operating with severely constrained sensing and communication, individuals may need to use direct physical proximity to facilitate information exchange, perform task-specific actions, or, crucially, both. Unfortunately, the sorts of densities ... More
Information Gathering in Decentralized POMDPs by Policy Graph ImprovementFeb 26 2019Decentralized policies for information gathering are required when multiple autonomous agents are deployed to collect data about a phenomenon of interest without the ability to communicate. Decentralized partially observable Markov decision processes ... More
Learning Multi-agent Communication under Limited-bandwidth Restriction for Internet Packet RoutingFeb 26 2019Communication is an important factor for the big multi-agent world to stay organized and productive. Recently, the AI community has applied the Deep Reinforcement Learning (DRL) to learn the communication strategy and the control policy for multiple agents. ... More
Market-Based Model in CR-WSN: A Q-Probabilistic Multi-agent Learning ApproachFeb 26 2019The ever-increasingly urban populations and their material demands have brought unprecedented burdens to cities. Smart cities leverage emerging technologies like the Internet of Things (IoT), Cognitive Radio Wireless Sensor Network (CR-WSN) to provide ... More
Anytime Heuristic for Weighted Matching Through Altruism-Inspired BehaviorFeb 25 2019We present a novel anytime heuristic (ALMA), inspired by the human principle of altruism, for solving the assignment problem. ALMA is decentralized, completely uncoupled, and requires no communication between the participants. We prove an upper bound ... More
Marathon Environments: Multi-Agent Continuous Control Benchmarks in a Modern Video Game EngineFeb 25 2019Recent advances in deep reinforcement learning in the paradigm of locomotion using continuous control have raised the interest of game makers for the potential of digital actors using active ragdoll. Currently, the available options to develop these ideas ... More
An Efficient Scheduling Algorithm for Multi-Robot Task Allocation in Assembling Aircraft StructuresFeb 24 2019Efficient utilization of cooperating robots in the assembly of aircraft structures relies on balancing the workload of the robots and ensuring collision-free scheduling. We cast this problem as that of allocating a large number of repetitive assembly ... More
Policies for growth of influence networks in task-oriented groups: elitism and egalitarianism outperform welfarismFeb 21 2019Communication or influence networks are probably the most controllable of all factors that are known to impact on the problem-solving capability of task-forces. In the case connections are costly, it is necessary to implement a policy to allocate them ... More
Survivable Networks via UAV Swarms Guided by Decentralized Real-Time Evolutionary ComputationFeb 21 2019The survivable network concept refers to contexts where the wireless communication between ground agents needs to be maintained as much as possible at all times, regardless of any adverse conditions that may arise. In this paper we propose a nature-inspired ... More
Regression-based Inverter Control for Decentralized Optimal Power Flow and Voltage RegulationFeb 20 2019Electronic power inverters are capable of quickly delivering reactive power to maintain customer voltages within operating tolerances and to reduce system losses in distribution grids. This paper proposes a systematic and data-driven approach to determine ... More
Empathic Autonomous AgentsFeb 20 2019Identifying and resolving conflicts of interests is a key challenge when designing autonomous agents. For example, such conflicts often occur when complex information systems interact persuasively with humans and are in the future likely to arise in non-human ... More
The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement LearningFeb 20 2019Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are ... More
Agent Madoff: A Heuristic-Based Negotiation Agent For The Diplomacy Strategy GameFeb 19 2019In this paper, we present the strategy of Agent Madoff, which is a heuristic-based negotiation agent that won 2nd place at the Automated Negotiating Agents Competition (ANAC 2017). Agent Madoff is implemented to play the game Diplomacy, which is a strategic ... More
On Voting Strategies and Emergent CommunicationFeb 19 2019Humans use language to collectively execute complex strategies in addition to using it as a referential tool for referring to physical entities. While existing approaches that study the emergence of language in settings where the language mainly acts ... More
Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement LearningFeb 18 2019In this paper, we propose a new learning technique named message-dropout to improve the performance for multi-agent deep reinforcement learning under two application scenarios: 1) classical multi-agent reinforcement learning with direct message communication ... More
Limited Lookahead in Imperfect-Information GamesFeb 17 2019Limited lookahead has been studied for decades in complete-information games. We initiate a new direction via two simultaneous deviation points: generalization to incomplete-information games and a game-theoretic approach. We study how one should act ... More
Optimizing Online Matching for Ride-Sourcing Services with Multi-Agent Deep Reinforcement LearningFeb 17 2019Ride-sourcing services are now reshaping the way people travel by effectively connecting drivers and passengers through mobile internets. Online matching between idle drivers and waiting passengers is one of the most key components in a ride-sourcing ... More
PT-ISABB: A Hybrid Tree-based Complete Algorithm to Solve Asymmetric Distributed Constraint Optimization ProblemsFeb 16 2019Asymmetric Distributed Constraint Optimization Problems (ADCOPs) have emerged as an important formalism in multi-agent community due to their ability to capture personal preferences. However, the existing search-based complete algorithms for ADCOPs can ... More
PT-ISABB: A Hybrid Tree-based Complete Algorithm to Solve Asymmetric Distributed Constraint Optimization ProblemsFeb 16 2019Mar 04 2019Asymmetric Distributed Constraint Optimization Problems (ADCOPs) have emerged as an important formalism in multi-agent community due to their ability to capture personal preferences. However, the existing search-based complete algorithms for ADCOPs can ... More
Privacy of Existence of Secrets: Introducing Steganographic DCOPs and Revisiting DCOP FrameworksFeb 15 2019Here we identify a type of privacy concern in Distributed Constraint Optimization (DCOPs) not previously addressed in literature, despite its importance and impact on the application field: the privacy of existence of secrets. Science only starts where ... More
Matchings under Preferences: Strength of Stability and Trade-offsFeb 15 2019We propose two solution concepts for matchings under preferences: robustness and near stability. The former strengthens while the latter relaxes the classic definition of stability by Gale and Shapley (1962). Informally speaking, robustness requires that ... More
A Subjective-Logic-based Reliability Estimation Mechanism for Cooperative Information with Application to IV's SafetyFeb 12 2019Use of cooperative information, distributed by road-side units, offers large potential for intelligent vehicles (IVs). As vehicle automation progresses and cooperative perception is used to fill the blind spots of onboard sensors, the question of reliability ... More
The StarCraft Multi-Agent ChallengeFeb 11 2019In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents ... More
The StarCraft Multi-Agent ChallengeFeb 11 2019Feb 26 2019In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents ... More
Exploration of High-Dimensional Grids by Finite State MachinesFeb 11 2019We consider the problem of finding a treasure at an unknown point of an $n$-dimensional infinite grid, $n\geq 3$, by initially collocated finite state agents (scouts/robots). Recently, the problem has been well characterized for 2 dimensions for deterministic ... More
Understanding The Impact of Partner Choice on Cooperation and Social Norms by means of Multi-agent Reinforcement LearningFeb 08 2019Feb 13 2019The human ability to coordinate and cooperate has been vital to the development of societies for thousands of years. While it is not fully clear how this behavior arises, social norms are thought to be a key factor in this development. In contrast to ... More
Understanding The Impact of Partner Choice on Cooperation and Social Norms by means of Multi-agent Reinforcement LearningFeb 08 2019The human ability to coordinate and cooperate has been vital to the development of societies for thousands of years. While it is not fully clear how this behavior arises, social norms are thought to be a key factor in this development. In contrast to ... More
Hierarchical Critics Assignment for Multi-agent Reinforcement LearningFeb 08 2019In this paper, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of multi-agent reinforcement learning (MARL) tasks. Within the actor-critic MARL, we introduce multiple cooperative critics ... More
Hierarchical Critics Assignment for Multi-agent Reinforcement LearningFeb 08 2019Feb 11 2019In this paper, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of multi-agent reinforcement learning (MARL) tasks. Within the actor-critic MARL, we introduce multiple cooperative critics ... More
A Framework for Autonomous Robot Deployment with Perfect Demand Satisfaction using Virtual ForcesFeb 08 2019In many applications, robots autonomous deployment is preferable and sometimes it is the only affordable solution. To address this issue, virtual force (VF) is one of the prominent approaches to performing multirobot deployment autonomously. However, ... More
A Unified Dissertation on Bearing Rigidity TheoryFeb 07 2019Accounting for the current state-of-the-art, this work aims at summarizing the main notions about the bearing rigidity theory, namely the branch of knowledge investigating the structural properties for multi-element systems necessary to preserve the inter-units ... More
Distributed Synthesis of Surveillance Strategies for Mobile SensorsFeb 06 2019We study the problem of synthesizing strategies for a mobile sensor network to conduct surveillance in partnership with static alarm triggers. We formulate the problem as a multi-agent reactive synthesis problem with surveillance objectives specified ... More
CESMA: Centralized Expert Supervises Multi-AgentsFeb 06 2019Feb 07 2019We consider the reinforcement learning problem of training multiple agents in order to maximize a shared reward. In this multi-agent system, each agent seeks to maximize the reward while interacting with other agents, and they may or may not be able to ... More
CLEAR: A Consistent Lifting, Embedding, and Alignment Rectification Algorithm for Multi-Agent Data AssociationFeb 06 2019A fundamental challenge in many robotics applications is to correctly synchronize and fuse observations across a team of sensors or agents. Instead of solely relying on pairwise matches among observations, multi-way matching methods leverage the notion ... More
Agent-Based Simulation Modelling for Reflecting on Consequences of Digital Mental HealthFeb 05 2019The premise of this working paper is based around agent-based simulation models and how to go about creating them from given incomplete information. Agent-based simulations are stochastic simulations that revolve around groups of agents that each have ... More
Learning to Schedule Communication in Multi-agent Reinforcement LearningFeb 05 2019Many real-world reinforcement learning tasks require multiple agents to make sequential decisions under the agents' interaction, where well-coordinated actions among the agents are crucial to achieve the target goal better at these tasks. One way to accelerate ... More
COME TOGETHER: Multi-Agent Geometric Consensus (Gathering, Rendezvous, Clustering, Aggregation)Feb 04 2019This report surveys results on distributed systems comprising mobile agents that are identical and anonymous, oblivious and interact solely by adjusting their motion according to the relative location of their neighbours. The agents are assumed capable ... More
On the Enactability of Agent Interaction Protocols: Toward a Unified ApproachFeb 04 2019Feb 13 2019Interactions between agents are usually designed from a global viewpoint. However, the implementation of a multi-agent interaction is distributed. This difference can introduce issues. For instance, it is possible to specify protocols from a global viewpoint ... More
Cooperative Driving at Unsignalized Intersections Using Tree SearchFeb 04 2019In this paper, we propose a new cooperative driving strategy for connected and automated vehicles (CAVs) at unsignalized intersections. Based on the tree representation of the solution space for the passing order, we combine Monte Carlo tree search (MCTS) ... More
On Steering SwarmsFeb 01 2019The main contribution of this paper is a novel method allowing an external observer/controller to steer and guide swarms of identical and indistinguishable agents, in spite of the agents' lack of information on absolute location and orientation. Importantly, ... More
Probabilistic Gathering Of Agents With Simple SensorsFeb 01 2019We present a novel probabilistic gathering algorithms for agents that can only detect the presence of other agents in front or behind them. The agents act in the plane and are identical and indistinguishable, oblivious and lack any means of direct communication. ... More
Distributionally Robust Removal of Malicious Nodes from NetworksJan 31 2019An important problem in networked systems is detection and removal of suspected malicious nodes. A crucial consideration in such settings is the uncertainty endemic in detection, coupled with considerations of network connectivity, which impose indirect ... More
Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement LearningJan 31 2019A fundamental question in any peer-to-peer ridesharing system is how to, both effectively and efficiently, dispatch user's ride requests to the right driver in real time. Traditional rule-based solutions usually work on a simplified problem setting, which ... More
ACSEE: Antagonistic Crowd Simulation model with Emotional contagion and Evolutionary gameJan 31 2019Antagonistic crowd behaviors are often observed in cases of serious conflict. Antagonistic emotions between different opposing groups and the way they spread through contagion in a crowd are important causes of such behaviors. Moreover, games between ... More
Priority Inheritance with Backtracking for Iterative Multi-agent Path FindingJan 31 2019Mar 07 2019The Multi-agent Path Finding (MAPF) problem consists in all agents having to move to their own destinations while avoiding collisions. In practical applications to the problem, such as for navigation in an automated warehouse, MAPF must be solved iteratively. ... More
Determining r- and (r,s)-Robustness of Digraphs Using Mixed Integer Linear ProgrammingJan 30 2019There has been an increase in the use of resilient control algorithms based on the graph theoretic properties of $r$- and $(r,s)$-robustness. These algorithms guarantee consensus of normally behaving agents in the presence of a bounded number of arbitrarily ... More
Coordinating the Crowd: Inducing Desirable Equilibria in Non-Cooperative SystemsJan 30 2019Many real-world systems such as taxi systems, traffic networks and smart grids involve self-interested actors that perform individual tasks in a shared environment. However, in such systems, the self-interested behaviour of agents produces welfare inefficient ... More
Directed Formation Control of n Planar Agents with Distance and Area ConstraintsJan 29 2019Feb 04 2019In this paper, we take a first step towards generalizing a recently proposed method for dealing with the problem of convergence to incorrect equilibrium points of distance-based formation controllers. Specifically, we introduce a distance and area-based ... More
A Regulation Enforcement Solution for Multi-agent Reinforcement LearningJan 29 2019Human behaviors are regularized by a variety of norms or regulations, either to maintain orders or to enhance social welfare. If artificial intelligent (AI) agents make decisions on behalf of human beings, we would hope they can also follow established ... More
Space and complexities of territorial systemsJan 28 2019The spatial character of territorial systems plays a crucial role in the emergence of their complexities. This contribution aims at illustrating to what extent different types of complexities can be exhibited in models of such systems. We develop from ... More
A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise InsertionJan 27 2019In this work we present a randomized gossip algorithm for solving the average consensus problem while at the same time protecting the information about the initial private values stored at the nodes. We give iteration complexity bounds for the method ... More
Multi-Agent Generalized Recursive ReasoningJan 26 2019We propose a new reasoning protocol called generalized recursive reasoning (GR2), and embed it into the multi-agent reinforcement learning (MARL) framework. The GR2 model defines reasoning categories: level-$0$ agent acts randomly, and level-$k$ agent ... More
Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent PoliciesJan 25 2019Decision making in multi-agent systems (MAS) is a great challenge due to enormous state and joint action spaces as well as uncertainty, making centralized control generally infeasible. Decentralized control offers better scalability and robustness but ... More
Feudal Multi-Agent Hierarchies for Cooperative Reinforcement LearningJan 24 2019We investigate how reinforcement learning agents can learn to cooperate. Drawing inspiration from human societies, in which successful coordination of many individuals is often facilitated by hierarchical organisation, we introduce Feudal Multi-agent ... More
Almost Envy-Freeness in Group Resource AllocationJan 24 2019We study the problem of fairly allocating indivisible goods between groups of agents using the recently introduced relaxations of envy-freeness. We consider the existence of fair allocations under different assumptions on the valuations of the agents. ... More
Open-ended Learning in Symmetric Zero-sum GamesJan 23 2019Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them `winner' and `loser'. If the game is approximately transitive, then self-play generates sequences of agents of increasing strength. ... More
Robust temporal difference learning for critical domainsJan 23 2019We present a new Q-function operator for temporal difference (TD) learning methods that explicitly encodes robustness against significant rare events (SRE) in critical domains. The operator, which we call the $\kappa$-operator, allows to learn a safe ... More
Second Order Statistics Analysis and Comparison between Arithmetic and Geometric Average FusionJan 23 2019Two fundamental approaches to information averaging are based on linear and logarithmic combination, yielding the arithmetic average (AA) and geometric average (GA) of the fusing initials, respectively. In the context of target tracking, the two most ... More
Cooperative coevolution of real predator robots and virtual robots in the pursuit domainJan 23 2019The pursuit domain, or predator-prey problem is a standard testbed for the study of coordination techniques. In spite that its problem setup is apparently simple, it is challenging for the research of the emerged swarm intelligence. This paper presents ... More
Single Deep Counterfactual Regret MinimizationJan 22 2019Feb 10 2019Counterfactual Regret Minimization (CFR) is the most successful algorithm for finding approximate Nash equilibria in imperfect information games. However, CFR's reliance on full game-tree traversals limits its scalability. For this reason, the game's ... More
Approval-Based Elections and Distortion of Voting RulesJan 20 2019We consider elections where both voters and candidates can be associated with points in a metric space and voters prefer candidates that are closer to those that are farther away. It is often assumed that the optimal candidate is the one that minimizes ... More
Resource-aware IoT Control: Saving Communication through Predictive TriggeringJan 19 2019The Internet of Things (IoT) interconnects multiple physical devices in large-scale networks. When the 'things' coordinate decisions and act collectively on shared information, feedback is introduced between them. Multiple feedback loops are thus closed ... More
Computing large market equilibria using abstractionsJan 18 2019Computing market equilibria is an important practical problem for market design (e.g. fair division, item allocation). However, computing equilibria requires large amounts of information (e.g. all valuations for all buyers for all items) and compute power. ... More
Theory of Minds: Understanding Behavior in Groups Through Inverse PlanningJan 18 2019Human social behavior is structured by relationships. We form teams, groups, tribes, and alliances at all scales of human life. These structures guide multi-agent cooperation and competition, but when we observe others these underlying relationships are ... More
H${}^2$CM-based holonic modeling of a gas pipelineJan 17 2019A gas pipeline is a relatively simple physical system, but the optimality of the control is difficult to achieve. When switching from one kind of gas to another , a volume of useless mixture is generated. Therefore, the control needs to both respond to ... More