New Zealand

AAMAS 2020

Orthos: A Trustworthy AI Framework for Data Acquisition

decentralized applications

spatio-temporal data-acquisition

smart contracts

trustworthy ai

AIAI 2020 (16th International Conference on Artificial Intelligence Applications and Innovations) should be held in Halkidiki, Greece. Due to current Covid-19 situation the conference will be held virtually. Underline will host a repository of video talks and preserve them for the future. Videos will be released on Underline one day after the conference.

AIAI 2020

technical paper

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). 

Modern interactive software, such as computer games, employ complex user interfaces. Although these user interfaces make the games attractive and powerful, unfortunately they also make them extremely difficult to test. Not only do we have to deal with their functional complexity, but also the fine grained interactivity of their user interface blows up their interaction space. A space so complex, that traditional automated testing techniques have trouble handling it. An agent-based testing approach offers an alternative solution. The agents' goal driven planning, adaptivity, and reasoning ability can provide an extra edge towards effective navigation in complex interaction space. This paper presents aplib, a Java library for programming intelligent test agents, featuring novel tactical programming as an abstract way to exert control over agents' underlying reasoning-based behavior. This type of control is suitable for programming testing tasks. Aplib is implemented in such a way to provide the fluency of a Domain Specific Language (DSL). Its embedded DSL approach also means that aplib programmers will get all the advantages that Java programmers get: rich language features and a whole array of development tools.

Aplib: Tactical Agents for Testing Computer Games

I briefly motivate the project presented by the paper. The contributions of the paper are outlined. I argue for the use of Blocks World for Teams environment. I briefly describe a transformation of GOAL code to agent logic, and how this leads into proving correctness of agents. Finally, I sketch future steps for the project by identifying key challenges.

A Verification Framework for GOAL Agents

An update on the First Intention Progression Competition.

Intention Progression Competition Update

Complex machine learning models are regularly used in critical decision-making domains, as black-box algorithms. This has given rise to several calls for algorithmic explainability. Many explanation algorithms proposed in literature assign importance to each feature individually. However, such explanations fail to capture the joint effects of sets of features. Indeed, few works so far formally analyze high dimensional model explanations. In this paper, we propose a novel high dimension model explanation method that captures the joint effect of feature subsets. We propose a new axiomatization for a generalization of the Banzhaf Index; our method can also be thought of as an approximation of a black-box model by a higher-order polynomial. In other words, this work justifies the use of the generalized Banzhaf index as a model explanation by showing that it uniquely satisfies a set of natural desiderata and that it is the optimal local approximation of a black-box model.

High Dimensional Model Explanations: an Axiomatic Approach

Centrality measures are among the most fundamental tools for social network analysis. Since network data is often incomplete, erroneous, or otherwise manipulated, increasing attention has recently been paid to studying the sensitivity of centrality measures to such distortions. However, thus far no universal method of quantifying the manipulability of centrality measures has been proposed. To bridge this gap in the literature, we take an axiomatic approach. In particular, we introduce a set of intuitive axioms that characterize such a measure, and prove that there exists only one solution that satisfies them. Next, building upon this measure, we quantify the manipulability of the most fundamental centrality measures.

The Manipulability of Centrality Measures—An Axiomatic Approach

The circadian rhythm is responsible for the daily variations in metabolism, and circadian rhythm disorders have direct implications for many diseases, such as obesity and mental disorders. The regulation of sleep time is the most common example of the importance of the circadian rhythm for the functioning of the human body. In this sense, this work aims to study a mathematical and computational model based on multiagent simulation that simulates the synchronization and desynchronization of the circadian rhythm in relation to the pain variables. The results from the multiagent simulation of circadian rhythms show that in relation to pain, sleep, especially its biological rhythms, is directly affected by pain. In this way, our mathematical model was able to show that pain causes changes in the circadian rhythm and it can contribute to the medical field analysis.

Circadian Rhythm and Pain: Mathematical Model based on Multiagent Simulation

Reactive behaviour in BDI-based models and architectures adopted in Agent Programming is typically modelled in terms of reactive plans not bound to any specific goal. In this paper we present and discuss an extension of the plan model used in BDI in which goal-based plans encapsulate both proactive and reactive behaviour. This brings important benefits both in the practice of agent program- ming and in supporting agent reasoning at runtime. The paper first introduced the model formally and then its evaluation through two concrete implementations, based on two existing agent program- ming platforms i.e. Jason and ASTRA.

Encapsulating Reactive Behaviour in Goal-based Plans in BDI Agents Programming

Reinforcement Learning (RL) has been widely used to solve sequential decision-making problems. However, RL algorithms suffer from poor sample efficiency and require a long time to learn a suitable policy, especially when multiple agents are learning without prior knowledge. This problem can be alleviated through reusing knowledge from other agents during the learning process. One notable approach is advising actions based on a teacher-student relationship, where the decision of a student agent during learning is aided by an experienced teacher agent. A critical assumption in teacher-student paradigm is that the communication may be limited, so that a student may wait for a while and learn by itself before receiving the next advice. More importantly, in some noisy or stochastic environments, the student may not be able to mas- ter the advised actions when they are only performed once. We propose three methods for agents choosing between learning by exploration, asking for advice and reusing previous advice. The results show that our approaches significantly outperform existing advising methods without reusing advice.


Learning by Reusing Previous Advice in Teacher-Student Paradigm

"This paper evaluates the applicability of reinforcement learning (RL) to multi-product inventory management in supply chains. The novelty of this problem with respect to supply chain literature is (i) we consider concurrent inventory management of a large number (hundreds) of products under realistic constraints such as shared capacity, and (ii) the number of products (size of the problem) can change frequently, implying that the RL agent needs to work in this regime without retraining. We approach the problem as a special class of dynamical system control, and explain why the generic problem cannot be satisfactorily solved using classical optimisation techniques. Subsequently, we formulate the problem in a
reinforcement learning framework that can be used for parallelised decision-making, and use the advantage actor critic (A2C) and deep Q-network (DQN) algorithms with quantised action spaces to solve the problem. Experiments on scales between 100 and 220 products
show that these approaches perform better than other baseline algorithms. They are also able to transfer learning without retraining, when the number of products change."

Using Reinforcement Learning for a Large Variable-Dimensional Inventory Management Problem

Recent advances in artificial intelligence (AI) have drawn attention to the need for AI systems to be understandable to human users. The explainable AI (XAI) literature aims to enhance human understanding and human-AI team performance by providing users with necessary information about AI system behavior. Simultaneously, the human factors literature has long addressed important considerations that contribute to human performance, including how to determine human informational needs.
 Drawing from the human factors literature, we propose a three-level framework for the development and evaluation of explanations about AI system behavior. Our proposed levels of XAI are based on the informational needs of human users, which can be determined using the levels of situation awareness (SA) framework from the human factors literature. Based on our levels of XAI framework, we also propose a method for assessing the effectiveness of XAI systems.

Downloads

Next from AAMAS 2020

Aplib: Tactical Agents for Testing Computer Games

Similar lecture

Trustworthy AI Needs Unbiased Dictators!

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

Aplib: Tactical Agents for Testing Computer Games

Similar lecture

Trustworthy AI Needs Unbiased Dictators!

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads