New Zealand

Stefan K. Behfar (March 4th 2020). Importance of Social Networks for Knowledge Sharing and the Impact of Collaboration on Network Innovation in Online Communities, Harnessing Knowledge, Innovation and Competence in Engineering of Mission Critical Systems, Ali G. Hessami, IntechOpen, DOI: 10.5772/intechopen.89605. 

Igor Goncharov, Nikita Goncharov, Pavel Parinov, Sergey Kochedykov and Alexander Dushkin (August 20th 2019). Modelling the Information-Psychological Impact in Social Networks, Probability, Combinatorics and Control, Andrey Kostogryzov and Victor Korolev, IntechOpen, DOI: 10.5772/intechopen.88252. 

AAMAS 2020

Conventional Traffic Management System

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

technical paper

a-Rank: Practically Scaling a-Rank through Stochatic Optimisation

A dark pool is a private forum for trading financial instruments such as equities and derivatives. The service is offered to traders, often representing large financial institutions, who aim to make large trades without telegraphing their intentions in a public venue such as the New York Stock Exchange or NASDAQ. Internally, the dark pool operates just like a public exchange, but the order book, a list of offers to buy and sell, is not visible to any of the participants. Only when matching orders are found the trade is executed and reported externally. Because the large orders are not visible to others, the risk of significant price moves is reduced. 

The operators of dark pools are trustworthy, but traders are notoriously suspicious. Traders are concerned about any ``leakage'' of information that might alert others to their intentions and cause price moves against them. The operator sees all orders posted by all participants, including sensitive information such as the volume of the order and the bid or ask price. Because the operator of the dark pool is usually a large financial institution with its own investments in the assets being traded, it may have conflicts of interest with the clients it serves in the dark pool. While such conflicts are mitigated by law and regulation, they continue to exist.

We propose new mechanism that reduce the need of traders to trust the operator of the dark pool. By adopting cryptographic techniques, we achieve a fully private and secure marketplace where sellers and buyers interact with the operator without exposing the volumes or prices of their orders to the operator or to any other counter party. These values remain secret until a matching order is found, and only afterward it will be revealed publicly. This provides a strictly stronger privacy guarantee compared to ordinary dark pools, and may lead to an increase in the trust of the participants to the system and reduce tension between participants and the operator.

Privacy Preserving Dark Pools

"On-demand ride-pooling (e.g., UberPool) has recently become popular because of its ability to lower costs for passengers while simultaneously increasing revenue for drivers and aggregation companies. Unlike in Taxi on Demand (ToD) services – where a vehicle is only assigned one passenger at a time – in on-demand ride-pooling, each (possibly partially filled) vehicle can be assigned a group of passenger requests with multiple different origin and destination pairs. To ensure near real-time response, existing solutions to the real-time ride-pooling problem are myopic in that they optimise the objective (e.g., maximise the number of passengers served) for the current time step without considering its effect on future assignments. This is because even a myopic assignment in ride-pooling involves considering what combinations of passenger requests that can be assigned to vehicles, which adds a layer of combinatorial complexity to the ToD problem.

A popular approach that addresses the limitations of myopic assignments in ToD problems is Approximate Dynamic Programming (ADP). Existing ADP methods for ToD can only handle Linear Program (LP) based assignments, however, while the assignment problem in ride-pooling requires an Integer Linear Program (ILP) with bad LP relaxations. To this end, our key technical contribution is in providing a general ADP method that can learn from ILP-based assignments. Additionally, we handle the extra combinatorial complexity from combinations of passenger requests by using a Neural Network based approximate value function and show a connection to Deep Reinforcement Learning that allows us to learn this value-function with increased stability and sample-efficiency. We show that our approach outperforms past approaches on a real-world dataset by up to 16%, a significant improvement in city-scale transportation problems."

Neural Approximate Dynamic Programming for On-Demand Ride-Pooling

Large-scale screening for potential threats with limited resources and capacity for screening is a problem of interest at airports, seaports, and other ports of entry. Adversaries can observe screening procedures and arrive at a time when there will be gaps in screening due to limited resource capacities. To capture this game between ports and adversaries, this problem has been previously represented as a Stackelberg game, referred to as a Threat Screening Game (TSG). Given the significant complexity associated with solving TSGs and uncertainty in arrivals of customers, existing work has assumed that screenees arrive and are allocated security resources at the beginning of the time-window. In practice, screenees such as airport passengers arrive in bursts correlated with flight time and are not bound by fixed time-windows. To address this, we propose an online threat screening model in which the screening strategy is determined adaptively as a passenger arrives while satisfying a hard bound on acceptable risk of not screening a threat. To solve the online problem, we first reformulate it as a Markov Decision Process (MDP) in which the hard bound on risk translates to a constraint on the action space and then solve the resultant MDP using Deep Reinforcement Learning (DRL). To this end, we provide a novel way to efficiently enforce linear inequality constraints on the action output in DRL. We show that our solution allows us to significantly reduce screenee wait time without compromising on the risk.

Solving Online Threat Screening Games using Constrained Action Space Reinforcement Learning

Mitingating the Negative Side Effects of Reasoning with Imperfect Models: A Mult - Objective Approach

A variety of constructive manipulation, control, and bribery for approval-based multi-winner voting have been extensively studied very recently. However, their destructive counterparts seem to be less studied in the literature so far. This paper aims to fill this gap by exploring the complexity of several destructive bribery problems under five prestigious approval-based multi-winner voting rules. Generally speaking, these problems are to determine if a number of given candidates can be excluded from any winning committees by performing a series of modification operations yet without exceeding a given budget. We consider five operations. We offer a complete landscape of the complexity of the problems studied in this paper, and for NP-hard problems we study their parameterized complexity with respect to meaningful parameters.

On the Complexity of Destructive Bribery in Approval-Based Multiwinner Voting

"Peer-to-peer ridesharing (P2P-RS) enables people to arrange one-time rides with their own private cars, without the involvement of professional drivers. It is a prominent collective intelligence application producing significant benefits both for individuals (reduced costs) and for the entire community (reduced pollution and traffic), as we showed in a recent publication where we proposed an online approximate solution algorithm for large-scale P2P-RS.
In this paper we tackle the fundamental question of assessing the benefit of predicting ridesharing requests in the context of P2P-RS optimisation. 
Results on a public real-world show that, by employing a perfect predictor, the total reward can be improved by 5.27% with a forecast horizon of $1$ minute.
On the other hand, a vanilla long short-term memory neural network cannot improve upon a baseline predictor that simply replicates the previous day's requests, whilst achieving an almost-double accuracy"

Predicting Requests in Large-Scale Online P2P Ridesharing

Motivated by the apparent societal need to design complex autonomous systems whose decisions and actions are humanly intelligible, the study of explainable artificial intelligence, and with it, research on explainable autonomous agents has gained increased attention from the research community. One important objective of research on explainable agents is the evaluation of explanation approaches in human-computer interaction studies. In this demonstration paper, we present a way to facilitate such studies by implementing explainable agents and multi-agent systems that i) can be deployed as static files, not requiring the execution of server-side code, which minimizes administration and operation overhead, and ii) can be embedded into web front ends and other JavaScript-enabled user interfaces, hence increasing the ability to reach a broad range of users. We then demonstrate the approach with the help of an application that was designed to assess the effect of different explainability approaches on the human intelligibility of an unmanned aerial vehicle simulation.

Explainable Agents as Static Web Pages: UAV Simulation Example

We propose a novel method for analyzing and visualizing the complexity of standard reinforcement learning (RL) benchmarks based on score distributions. A large number of policy networks are generated by randomly guessing their parameters, and then evaluated on the benchmark task; the study of their aggregated results provide insights into the benchmark complexity. Our method guarantees objectivity of evaluation by sidestepping learning altogether: the policy network parameters are generated using Random Weight Guessing (RWG), making our method agnostic to (i) the classic RL setup, (ii) any learning algorithm, and (iii) hyperparameter tuning. We show that this approach isolates the environment complexity, highlights specific types of challenges, and provides a proper foundation for the statistical analysis of the task's difficulty. We test our approach on a variety of classic control benchmarks from the OpenAI Gym, where we show that small untrained networks can provide a robust baseline for a variety of tasks. The networks generated often show good performance even without gradual learning, incidentally highlighting the triviality of a few popular benchmarks.

Analyzing Reinforcement Learning Benchmarks using Random Weight Guessing

Multiagent systems can use commitments as the core of a general coordination infrastructure, supporting both cooperative and non-cooperative interactions. For agents whose objectives are aligned, and where one agent can help another achieve greater reward by sacrificing some of its own reward, their cooperative commitment should be chosen to maximize their joint reward. We present a solution to the problem of how cooperative agents can efficiently find an (approximately) optimal commitment by querying about carefully selected commitment choices. We prove structural properties of the agents' values as functions of the parameters of the commitment specification, and develop a greedy method for composing a query with provable approximation bounds, that we empirically show can find nearly optimal commitments in a fraction of the time that methods that lack our insights require.

Downloads

Next from AAMAS 2020

a-Rank: Practically Scaling a-Rank through Stochatic Optimisation

Similar lecture

Distance Hedonic Games

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAMAS 2020

a-Rank: Practically Scaling a-Rank through Stochatic Optimisation

Similar lecture

Distance Hedonic Games

Downloads