The problem of specifying high-level knowledge bases for planning becomes a hard task in realistic environments. This knowledge is usually handcrafted and is hard to keep updated, even for system experts. Recent approaches have shown the success of classical planning at synthesizing action models even when all intermediate states are missing. These approaches can synthesize action schemas in Planning Domain Definition Language (PDDL) from a set of execution traces each consisting, at least, of an initial and final state. In this paper, we propose a new algorithm to unsupervisedly synthesize STRIPS action models with a classical planner when action signatures are unknown. In addition, we contribute with a compilation to classical planning that mitigates the problem of learning static predicates in the action model preconditions, exploits the capabilities of SAT planners with parallel encodings to compute action schemas and validate all instances. Our system is flexible in that it supports the inclusion of partial input information that may speed up the search. We show through several experiments how learned action models generalize over unseen planning instances.

In this paper, we present an extension to an air traffic conflicts resolution method consisting in generating a large number of trajectories for a set of aircraft, and efficiently selecting the best compatible ones. We propose a multimanoeuvre version which encapsulates different conflict-solving algorithms, in particular an original "smart brute-force" method and the well-known ToulBar2 CSP toolset. Experiments on several benchmarks show that the first one is very efficient on cases involving few aircraft (representative of what actually happens in operations), allowing us to search through a large pool of manoeuvres and trajectories; however, this method is overtaken by its complexity when the number of aircraft increases to 7 and more. Conversely, within acceptable times, the ToulBar2 toolset can handle conflicts involving more aircraft, but with fewer possible trajectories for each.

Graphs can be used to represent and reason about real world systems. A variety of metrics have been devised to quantify their global characteristics. In general, prior work focuses on measuring the properties of existing graphs rather than the problem of dynamically modifying them (for example, by adding edges) in order to improve the value of an objective function. In this paper, we present RNet-DQN, a solution for improving graph robustness based on Graph Neural Network architectures and Deep Reinforcement Learning. We investigate the application of this approach for improving graph robustness, which is relevant to infrastructure and communication networks. We capture robustness using two objective functions and use changes in their values as the reward signal. Our experiments show that our approach can learn edge addition policies for improving robustness that perform significantly better than random and, in some cases, exceed the performance of a greedy baseline. Crucially, the learned policies generalize to different graphs including those larger than the ones on which they were trained. This is important because the naive greedy solution can be prohibitively expensive to compute for large graphs; our approach offers an $O(|V|^3)$ speed-up with respect to it.

The world of competitive Esports and video gaming has seen and continues to experience steady growth in popularity and complexity. Correspondingly, more research on the topic is being published, ranging from social network analyses to the benchmarking of advanced artificial intelligence systems in playing against humans. In this paper, we present ongoing work on an intelligent agent recommendation engine that suggests actions to players in order to maximise success and enjoyment, both in the space of in-game choices, as well as decisions made around play session timing in the broader context. By leveraging temporal data and appropriate models, we show that a learned representation of player psychological momentum, and of tilt, can be used, in combination with player expertise, to achieve state-of-the-art performance in pre- and post-draft win prediction. Our progress toward fulfilling the potential for deriving optimal recommendations is documented.

Traditional multi-armed bandit strategies look to the history of observed rewards to identify the most promising arms for optimizing expected total reward in the long run. When considering limited time budgets and computational resources, this backward view of rewards is inappropriate as the bandit should look into the future for anticipating the highest final reward at the end of a specified time budget. This work addresses that insight by introducing HAMLET, which extends the bandit approach with learning curve extrapolation and computation time-awareness for selecting among a set of machine learning algorithms. Results show that the HAMLET V ariants 1-3 exhibit equal or better performance than other bandit-based algorithm selection strategies in experiments with recorded hyperparameter tuning traces for the majority of considered time budgets. The best performing HAMLET V ariant 3 combines learning curve extrapolation with the well-known upper confidence bound exploration bonus. That variant performs better than all non-HAMLET policies with statistical significance at the 95% level for 1,485 runs.

In this article, we propose a multimodal perspective to diagrammatic representations by sketching a description of what may be tentatively termed the diagrammatic mode . We consider diagrammatic representations in the light of contemporary multimodality theory and explicate what enables diagrammatic representations to integrate natural language, various forms of graphics, diagrammatic elements such as arrows, lines and other expressive resources into coherent organisations. We illustrate the proposed approach using two recent diagram corpora and show how a multimodal approach supports the empirical analysis of diagrammatic representations, especially in identifying diagrammatic constituents and describing their interrelations.

Active Learning (AL) is a human-in-the-loop Machine Learning paradigm favored for its ability to learn with fewer labeled instances, but the model's states and progress remain opaque to the annotators. Meanwhile, many recognize the benefits of model transparency for people interacting with ML models, as reflected by the surge of explainable AI (XAI) as a research field. However, explaining an evolving model introduces many open questions regarding its impact on the annotation quality and the annotator's experience. In this paper, we propose a novel paradigm of explainable active learning (XAL), by explaining the learning algorithm's prediction for the instance it wants to learn from and soliciting feedback from the annotator. We conduct an empirical study comparing the model learning outcome, human feedback content and the annotator experience with XAL, to that of traditional AL and coactive learning (providing the model's prediction without the explanation). Our study reveals benefits--supporting trust calibration and enabling additional forms of human feedback, and potential drawbacks--anchoring effect and frustration from transparent model limitations--of providing local explanations in AL. We conclude by suggesting directions for developing explanations that better support annotator experience in AL and interactive ML settings.

Deep reinforcement learning (RL) has achieved outstanding results in recent years, which has led a dramatic increase in the number of methods and applications. Recent works are exploring learning beyond single-agent scenarios and considering multi-agent scenarios. However, they are faced with lots of challenges and are seeking for help from traditional game-theoretic algorithms, which, in turn, show bright application promise combined with modern algorithms and boosting computing power. In this survey, we first introduce basic concepts and algorithms in single agent RL and multi-agent systems; then, we summarize the related algorithms from three aspects. Solution concepts from game theory give inspiration to algorithms which try to evaluate the agents or find better solutions in multi-agent systems. Fictitious self-play becomes popular and has a great impact on the algorithm of multi-agent reinforcement learning. Counterfactual regret minimization is an important tool to solve games with incomplete information, and has shown great strength when combined with deep learning.

A research team at Ben-Gurion University have created a simple projection system able to trick Tesla's Autopilot into seeing things that aren't actually there. Using commercially available drones and a cheap projector - the kind a person might use to watch television in an apartment of small home - the team projected a series of deceptive images onto the road. The images included false traffic lines, a false speed limit sign, and an image of Elon Musk himself, projected on the road as if her were an endangered pedestrian. The researchers collectively labeled all these different visual phenomena as'phantoms,' according to a report in ArsTechnica. While the Tesla they tested reacted to every phantom in some way, most of its responses were fairly mild.

Robots have been created by scientists that'sweat' like humans during demanding tasks to stop them overheating. Robotic technology is advancing every day and machines are being given more demanding tasks that generate more heat as a by product. This heat could cause the robot to malfunction if it doesn't cool down, which prompted researchers from Cornell University to look at how humans get cool. They developed a technique that allows machines to'sweat' off cooling liquid stored around the component responsible for moving and controlling the system. They developed a technique that allows machines to'sweat' off cooling liquid stored around the component responsible for moving and controlling the system It is still an early prototype with a number of problems including the sweating process causing the robot to struggle to move.