Search

Although deep reinforcement learning (DRL) methods have been successfully applied in challenging tasks, their application in real-world operational settings is challenged by methods' limited ability to provide explanations. Among the paradigms for explainability in DRL is the interpretable box design paradigm, where interpretable models substitute inner constituent models of the DRL method, thus making the DRL method "inherently" interpretable. In this paper we explore this paradigm and we propose XDQN, an explainable variation of DQN, which uses an interpretable policy model trained through mimicking. XDQN is challenged in a complex, real-world operational multi-agent problem, where agents are independent learners solving congestion problems. Specifically, XDQN is evaluated in three MARL scenarios, pertaining to the demand-capacity balancing problem of air traffic management. XDQN achieves performance similar to that of DQN, while its abilities to provide global models' interpretations and interpretations of local decisions are demonstrated.

The current Air Traffic Management (ATM) system worldwide has reached its limits in terms of predictability, efficiency and cost effectiveness. Different initiatives worldwide propose trajectory-oriented transformations that require high fidelity aircraft trajectory planning and prediction capabilities, supporting the trajectory life cycle at all stages efficiently. Recently proposed data-driven trajectory prediction approaches provide promising results. In this paper we approach the data-driven trajectory prediction problem as an imitation learning task, where we aim to imitate experts "shaping" the trajectory. Towards this goal we present a comprehensive framework comprising the Generative Adversarial Imitation Learning state of the art method, in a pipeline with trajectory clustering and classification methods. This approach, compared to other approaches, can provide accurate predictions for the whole trajectory (i.e. with a prediction horizon until reaching the destination) both at the pre-tactical (i.e. starting at the departure airport at a specific time instant) and at the tactical (i.e. from any state while flying) stages, compared to state of the art approaches.

In this article, we report on the efficiency and effectiveness of multiagent reinforcement learning methods (MARL) for the computation of flight delays to resolve congestion problems in the Air Traffic Management (ATM) domain. Specifically, we aim to resolve cases where demand of airspace use exceeds capacity (demand-capacity problems), via imposing ground delays to flights at the pre-tactical stage of operations (i.e. few days to few hours before operation). Casting this into the multiagent domain, agents, representing flights, need to decide on own delays w.r.t. own preferences, having no information about others' payoffs, preferences and constraints, while they plan to execute their trajectories jointly with others, adhering to operational constraints. Specifically, we formalize the problem as a multiagent Markov Decision Process (MA-MDP) and we show that it can be considered as a Markov game in which interacting agents need to reach an equilibrium: What makes the problem more interesting is the dynamic setting in which agents operate, which is also due to the unforeseen, emergent effects of their decisions in the whole system. We propose collaborative multiagent reinforcement learning methods to resolve demand-capacity imbalances: Extensive experimental study on real-world cases, shows the potential of the proposed approaches in resolving problems, while advanced visualizations provide detailed views towards understanding the quality of solutions provided.

In this paper, we study the problem of spatial link discovery (LD), focusing primarily on topological and proximity relations between spatial objects. The problem is timely due to the large number of sources that generate spatial data, including streaming sources (e.g., surveillance of moving objects) but also archival sources (such as static areas of interest). To address the problem of integrating data from such diverse sources, link discovery techniques are required to identify various spatial relations efficiently. Existing approaches typically adopt the filter and refine methodology by exploiting a blocking technique for effective filtering. In this paper, we present a new spatial LD technique, called MaskLink, that improves the effectiveness of the filtering step. We show that MaskLink outperforms the state-of-the-art algorithm for link discovery of topological relations, while also addressing some of its limitations, such as applicability for streaming data, low memory requirements, and parallelization. Furthermore, we show that MaskLink can be extended and generalized to the case of proximity-based link discovery, which has not been studied before for spatial data. Our empirical study demonstrates the superiority of MaskLink against the state-of-the-art in the case of topological relations, and its performance gain compared to a baseline technique in the case of proximity-based LD.

Analysis of moving objects behaviour requires surveillance data (i.e. spatio-temporal data concerning objects’ positional information), together with information about moving objects, occurring events and their context. Thus, data from disparate sources must be converted to a common format, integrated w.r.t. a specific model. This paper proposes a generic framework for generating RDF from heterogenous data formats - exploiting the specification of graph templates. We present and demonstrate the benefits of the proposed RDF generation process for the provision of semantically annotated data revolving around the notion of objects’ trajectory. The process is demonstrated for the population of the datAcron ontology using real-world domain-specific data sources.

The purpose of this work is to test the efficiency of specific intelligent classification algorithms when dealing with the domain of stroke medical diagnosis. The dataset consists of patient records of the ”Acute Stroke Unit”, Alexandra Hospital, Athens, Greece, describing patients suffering one of 5 different stroke types diagnosed by 127 diagnostic attributes / symptoms collected during the first hours of the emergency stroke situation as well as during the hospitalization and recovery phase of the patients. Prior to the application of the intelligent classifier the dimensionality of the dataset is further reduced using a variety of classic and state of the art dimensionality reductions techniques so as to capture the intrinsic dimensionality of the data. The results obtained indicate that the proposed methodology achieves prediction accuracy levels that are comparable to those obtained by intelligent classifiers trained on the original feature space.

Proceeding volume: Vol-918

Power Trading Agent Competition (Power TAC) is a recently developed smart grid power market simulator that represents one competition scenario of the Trading Agent Competitions (TAC) international forum. According to the recent liberalization of power systems, the idea of Power TAC is the development of agent- based architectures which will provide realistic tests for the creation of future electric power markets. In this paper, we summarize the analysis of i) negotiating agreements in the Power TAC Tariff Market ; and ii) approaches and methods that the CrocodileAgent uses to maximize its profit and balance its portfolio.