In this work, we explore how probabilistic programs can be used to represent policies in sequential decision problems. In this formulation, a probabilistic program is a black-box stochastic simulator for both the problem domain and the agent. We relate classic policy gradient techniques to recently introduced black-box variational methods which generalize to probabilistic program inference. We present case studies in the Canadian traveler problem, Rock Sample, and a benchmark for optimal diagnosis inspired by Guess Who. Each study illustrates how programs can efficiently represent policies using moderate numbers of parameters.

Artificial intelligence (AI) is intelligence exhibited by machines. In computer science, an ideal "intelligent" machine is a flexible rational agent that perceives its environment and takes actions that maximize its chance of success at some goal.[1] Colloquially, the term "artificial intelligence" is applied when a machine mimics "cognitive" functions that humans associate with other human minds, such as "learning" and "problem solving".[2] As machines become increasingly capable, facilities once thought to require intelligence are removed from the definition. For example, optical character recognition is no longer perceived as an exemplar of "artificial intelligence" having become a routine technology.[3] Capabilities still classified as AI include advanced Chess and Go systems and self-driving cars. AI research is divided into subfields[4] that focus on specific problems or on specific approaches or on the use of a particular tool or towards satisfying particular applications. The central problems (or goals) of AI research include reasoning, knowledge, planning, learning, natural language processing (communication), perception and the ability to move and manipulate objects.[5] General intelligence is among the field's long-term goals.[6] Approaches include statistical methods, computational intelligence, soft computing (e.g. machine learning), and traditional symbolic AI. Many tools are used in AI, including versions of search and mathematical optimization, logic, methods based on probability and economics. The AI field draws upon computer science, mathematics, psychology, linguistics, philosophy, neuroscience and artificial psychology. The field was founded on the claim that human intelligence "can be so precisely described that a machine can be made to simulate it."[7] This raises philosophical arguments about the nature of the mind and the ethics of creating artificial beings endowed with human-like intelligence, issues which have been explored by myth, fiction and philosophy since antiquity.[8] Attempts to create artificial intelligence has experienced many setbacks, including the ALPAC report of 1966, the abandonment of perceptrons in 1970, the Lighthill Report of 1973 and the collapse of the Lisp machine market in 1987. In the twenty-first century AI techniques became an essential part of the technology industry, helping to solve many challenging problems in computer science.[9]

Europe has a new speedcubing champion, Germany's Phillip Weyer. Weyer solved a Rubik's cube puzzle in an average time of 7.88 seconds in the Rubik's Cube European Championship 2016. The 2016 Championship held in Prague, Czech Republic, is the seventh Rubik's Cube European Championship. It had 18 categories, including the main category of the classic 3x3 cube, solving the cube blindfolded or only using the feet. Weyer told Reuters that it took years of hard work to get to the top.

We are pleased to welcome Dr. Ricardo Baeza-Yates to the NTENT Team! Ricardo will play a key role in fortifying NTENT's innovation leadership in semantic and natural language processing and in shaping the company's technology vision. Get to know a little more about him. You have significant experience in the search space; can you please tell us a little bit about your background? I did my PhD at Univ. of Waterloo on search algorithms related to the New Oxford English Dictionary project. At that time, the dictionary was the largest single file on the planet (a bit more than 500Mb) and searching through it was a challenge.

Different versions of this problem have received is coping with uncertainties arising from limited a-considerable attention from several research communities, e.g., priori knowledge of the environment. Acquiring necessary as a "pursuit-evasion game" in game theory [13], [14], as information and achieving the overall goal are complementary a "cow-path problem" in computer science [15] or as a subtasks that require adapting the motion of a robot during "coverage problem" in control [16], [17], but its solution for mission execution, typically accompanied by minimizing a a general probability distribution or a general geometry of the performance criterion. In this work we address an Optimal region is, to a large extent, still an open question. Effective Control Problem (OCP) for a robot with fourth-order dynamics approaches for the related persistent monitoring problem based that has to find, collect and move a finite number of on estimation [18], linear programming [19] or parametric objects to a designated spot in minimum time. The objects optimization [20] have been also been proposed. OCPs with with a-priori known masses are located in a bounded twodimensional uncertainties have also been addressed by certainty equivalent space, where the robot is capable of localizing event-triggered [21], minimax [22] and sampling-based [23] itself using a state-of-the-art simultaneous localization and optimization schemes.

This article reviews the last two IEEE Conference on Computational Intelligence and Games (CIG) StarCraft Artificial Intelligence (AI) Competitions organized by the authors; these were the fourth and fifth in a series of annual competitions initiated in 2011. StarCraft AI Competitions have been hosted in conjunction with three different events: the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE), CIG, and Student StarCraft AI Tournament (SSCAIT). The purpose of these competitions is to design bots that are able to autonomously and successfully play the StarCraft game by implementing real-time strategies. Recent results reveal the promising use of AI techniques in creating successful AI entries, but there is room for improvement with respect to the bots’ ability to adapt and learn to defeat humans and scripted AI bots.

The workshop program at the Eleventh Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment was held November 14–15, 2015 at the University of California, Santa Cruz, USA. The program included 4 workshops (one of which was a joint workshop): Artificial Intelligence in Adversarial Real-Time Games, Experimental AI in Games, Intelligent Narrative Technologies and Social Believability in Games, and Player Modeling. This article contains the reports of three of the four workshops.

Enforcing local consistencies in cost function networks is performed by applying so-called Equivalent Preserving Transformations (EPTs) to the cost functions. As EPTs transform the cost functions, they may break the property that was making local consistency enforcement tractable on a global cost function. A global cost function is called tractable projection-safe when applying an EPT to it is tractable and does not break the tractability property. In this paper, we prove that depending on the size r of the smallest scopes used for performing EPTs, the tractability of global cost functions can be preserved (r = 0) or destroyed (r > 1). When r = 1, the answer is indefinite. We show that on a large family of cost functions, EPTs can be computed via dynamic programming-based algorithms, leading to tractable projection-safety. We also show that when a global cost function can be decomposed into a Berge acyclic network of bounded arity cost functions, soft local consistencies such as soft Directed or Virtual Arc Consistency can directly emulate dynamic programming. These different approaches to decomposable cost functions are then embedded in a solver for extensive experiments that confirm the feasibility and efficiency of our proposal.

Recent work has shown how to improve delete relaxation heuristics by computing relaxed plans, i.e., the hFF heuristic, in a compiled planning task PiC which represents a given set C of fact conjunctions explicitly. While this compilation view of such partial delete relaxation is simple and elegant, its meaning with respect to the original planning task is opaque, and the size of PiC grows exponentially in |C|. We herein provide a direct characterization, without compilation, making explicit how the approach arises from a combination of the delete-relaxation with critical-path heuristics. Designing equations characterizing a novel view on h+ on the one hand, and a generalized version hC of hm on the other hand, we show that h+(PiC) can be characterized in terms of a combined hcplus equation. This naturally generalizes the standard delete-relaxation framework: understanding that framework as a relaxation over singleton facts as atomic subgoals, one can refine the relaxation by using the conjunctions C as atomic subgoals instead. Thanks to this explicit view, we identify the precise source of complexity in hFF(PiC), namely maximization of sets of supported atomic subgoals during relaxed plan extraction, which is easy for singleton-fact subgoals but is NP-complete in the general case. Approximating that problem greedily, we obtain a polynomial-time hCFF version of hFF(PiC), superseding the PiC compilation, and superseding the modified PiCce compilation which achieves the same complexity reduction but at an information loss. Experiments on IPC benchmarks show that these theoretical advantages can translate into empirical ones.

'Til your good is better and your better is best." H2O now has random hyperparameter search with time- and metric-based early stopping. Bergstra and Bengio[1] write on p. 281: Compared with neural networks configured by a pure grid search, we find that random search over the same domain is able to find models that are as good or better within a small fraction of the computation time. Even smarter means of searching the hyperparameter space are in the pipeline, but for most use cases random search does as well. Nearly all model algorithms used in machine learning have a set of tuning "knobs" which affect how the learning algorithm fits the model to the data.