Applying machine learning models to meteorological data brings many opportunities to the Geosciences field, such as predicting future weather conditions more accurately. In recent years, modeling meteorological data with deep neural networks has become a relevant area of investigation. These works apply either recurrent neural networks (RNNs) or some hybrid approach mixing RNNs and convolutional neural networks (CNNs). In this work, we propose STConvS2S (short for Spatiotemporal Convolutional Sequence to Sequence Network), a new deep learning architecture built for learning both spatial and temporal data dependencies in weather data, using fully convolutional layers. Computational experiments using observations of air temperature and rainfall show that our architecture captures spatiotemporal context and outperforms baseline models and the state-of-art architecture for weather forecasting task.

In synthesis, assumptions are constraints on the environment that rule out certain environment behaviors. A key observation here is that even if we consider systems with LTL f goals on finite traces, environment assumptions need to be expressed over infinite traces, since accomplishing the agent goals may require an unbounded number of environment action. To solve synthesis with respect to finite-trace LTL f goals under infinite-trace assumptions, we could reduce the problem to LTL synthesis. Unfortunately, while synthesis in LTL f and in LTLhave the same worst-case complexity (both 2EXPTIME-complete), the algorithms available for LTLsyn-thesis are much more difficult in practice than those for LTL f synthesis. In this work we show that in interesting cases we can avoid such a detour to LTLsynthesis and keep the simplicity of LTL f synthesis. Specifically, we develop a BDD-based fixpoint-based technique for handling basic forms of fairness and of stability assumptions. We show, empirically, that this technique performs much better than standard LTLsynthesis. Introduction In many situations we are interested in expressing properties over an unbounded but finite sequence of successive states. Linear-time Temporal Logic over finite traces ( LTL f) and its variants have been thoroughly investigated for doing so. There has been broad research for logical reasoning (De Gi-acomo and V ardi 2013; Li et al. 2019), synthesis (De Gi-acomo and V ardi 2015; Camacho et al. 2018), and planning (Camacho et al. 2017; De Giacomo and Rubin 2018). Recently synthesis under assumptions in LTL f has attracted specific interest (De Giacomo and Rubin 2018; Camacho, Bienvenu, and McIlraith 2018). First, planning for LTL f goals can be considered as a form of LTL f synthesis under assumptions, where the assumptions are the dynamics of the environment encoded in the planning domain (Green 1969; Camacho, Bienvenu, and McIlraith 2018; Aminof et al. 2018; Aminof et al. 2019). Synthesis under assumptions has been extensively studied in LTL, where environment assumptions are expressed as LTL formulas (Chatterjee and Henzinger 2007; Chatter-jee, Henzinger, and Jobstmann 2008; D'Ippolito et al. 2013; Bloem, Ehlers, and K onighofer 2015; Brenguier, Raskin, and Sankur 2017). In fact, LTL formulas can be used as assumptions as long as it is guaranteed that the environment is able to behave so as to keep the assumptions true, i.e., assumptions are environment realizable. Under these circumstances, it is possible to reduce synthesis for LTL goal ψ G under assumptions ψ A to standard synthesis for ψ A ψ G. Note that because of the guarantee of ψ A being environment realizable, no agent strategy can win ψ A ψ G by falsifying ψ A. See (Aminof et al. 2019) for a discussion.

--We introduce L EARN2 FIX, the first human-in-the-loop, semiautomatic repair technique when no bug oracle-except for the user who is reporting the bug-is available. Our approach negotiates with the user the condition under which the bug is observed. Only when a budget of queries to the user is exhausted, it attempts to repair the bug. A query can be thought of as the following question: "When executing this alternative test input, the program produces the following output; is the bug observed"? Through systematic queries, L EARN2 FIX trains an automatic bug oracle that becomes increasingly more accurate in predicting the user's response. Our key challenge is to maximize the oracle's accuracy in predicting which tests are bug-revealing given a small budget of queries. From the alternative tests that were labeled by the user, test-driven automatic repair produces the patch. Our experiments demonstrate that L EARN2 FIX learns a sufficiently accurate automatic oracle with a reasonably low labeling effort (lt. Given L EARN2 FIX's test suite, the GenProg test-driven repair tool produces a higher-quality patch (i.e., passing a larger proportion of validation tests) than using manual test suites provided with the repair benchmark. I NTRODUCTION Automatic program repair (APR) [1], [2] holds the promise of automating the tedious, manual task of patching bugs. In their seminal paper, Le Goues and colleagues [3] demonstrated that APR is both feasible and cost-effective even at the scale of several million lines of code. Given a failing test suite, APR changes the buggy program such that all test cases pass. However, what if no such test suite is available? Suppose, a user reports a bug and provides a test input to reproduce the bug. We envision a semiautomatic approach that keeps the human-in-the-loop and negotiates the condition under which the bug is observed before repairing the bug. Strategically, the user is asked: " F or this other input, the program produces that output; is the bug observed "? While the user might not have the expertise to understand the source code or to produce a patch, it seems reasonable to ask to distinguish expected from unexpected program behavior. Iteratively, an automatic bug oracle is trained to predict the user's responses with increasing accuracy. Using the trained oracle, the user can be asked more strategically.

Many real-world applications involve teams of agents that have to coordinate their actions to reach a common goal against potential adversaries. This paper focuses on zero-sum games where a team of players faces an opponent, as is the case, for example, in Bridge, collusion in poker, and collusion in bidding. The possibility for the team members to communicate before gameplay---that is, coordinate their strategies ex ante---makes the use of behavioral strategies unsatisfactory. We introduce Soft Team Actor-Critic (STAC) as a solution to the team's coordination problem that does not require any prior domain knowledge. STAC allows team members to effectively exploit ex ante communication via exogenous signals that are shared among the team. STAC reaches near-optimal coordinated strategies both in perfectly observable and partially observable games, where previous deep RL algorithms fail to reach optimal coordinated behaviors.

Learning from demonstrations is a useful way to transfer a skill from one agent to another. While most imitation learning methods aim to mimic an expert skill by following the demonstration step-by-step, imitating every step in the demonstration often becomes infeasible when the learner and its environment are different from the demonstration. In this paper, we propose a method that can imitate a demonstration composed solely of observations, which may not be reproducible with the current agent. Our method, dubbed selective imitation learning from observations (SILO), selects reachable states in the demonstration and learns how to reach the selected states. Our experiments on both simulated and real robot environments show that our method reliably performs a new task by following a demonstration. Videos and code are available at https://clvrai.com/silo .

We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a new formal structure, the lifted abstract Markov decision process (L-AMDP), PALM learns models that are independent and modular. Through our experiments, we show how PALM integrates planning and execution, facilitating a rapid and efficient learning of abstract, hierarchical models. We also demonstrate the increased potential for learned models to be transferred to new and related tasks.

In many scenarios, complete and incomplete information coexist. For this reason, the knowledge representation and database communities have long shown interest in simultaneously supporting the closed- and the open-world views when reasoning about logic theories. Here we consider the setting of querying possibly incomplete data using logic theories, formalized as the evaluation of an ontology-mediated query (OMQ) that pairs a query with a theory, sometimes called an ontology, expressing background knowledge. This can be further enriched by specifying a set of closed predicates from the theory that are to be interpreted under the closed-world assumption, while the rest are interpreted with the open-world view. In this way we can retrieve more precise answers to queries by leveraging the partial completeness of the data. The central goal of this paper is to understand the relative expressiveness of OMQ languages in which the ontology is written in the expressive Description Logic (DL) ALCHOI and includes a set of closed predicates. We consider a restricted class of conjunctive queries. Our main result is to show that every query in this non-monotonic query language can be translated in polynomial time into Datalog with negation under the stable model semantics. To overcome the challenge that Datalog has no direct means to express the existential quantification present in ALCHOI, we define a two-player game that characterizes the satisfaction of the ontology, and design a Datalog query that can decide the existence of a winning strategy for the game. If there are no closed predicates, that is in the case of querying a plain ALCHOI knowledge base, our translation yields a positive disjunctive Datalog program of polynomial size. To the best of our knowledge, unlike previous translations for related fragments with expressive (non-Horn) DLs, these are the first polynomial time translations.

Abstract--In medicine, a communicating virtual patient or doctor allows students to train in medical diagnosis and dev elop skills to conduct a medical consultation. In this paper, we describe a conversational virtual standardized patient sy stem to allow medical students to simulate a diagnosis strategy o f an abdominal surgical emergency. We exploited the semantic properties captured by distributed word representations t o search for similar questions in the virtual patient dialogue syste m. We created two dialogue systems that were evaluated on dataset s collected during tests with students. The first system based on handcrafted rules obtains 92.29% as F 1-score on the studied clinical case while the second system that combines rules an d semantic similarity achieves 94.88%. It represents an error reduction of 9.70% as compared to the rules-only-based system. The medical diagnosis practice is traditionally bedside taught. Theoretical courses are supplemented by internshi ps in hospital services. The medical student observes the practi ce of doctors and interns and practices himself under their contr ol. This type of learning has the disadvantage to confront immediately the medical student with complex situations withou t practical training (technical and human) beforehand.

The names of actual companies and products mentioned herein may be the trademarks of their respective owners.

Recent research from SAP and Oxford Economics demonstrated CFOs' strategic initiatives are taking a more active role in the direction of their businesses, rather than operating within a siloed financial function. The report showed that 88% respondents said CFO's are increasingly involved in the strategic decisions of their organisations.