A robot that evoked a human form paused in front of a door leading to a simulated nuclear power plant accident and inexplicably stood motionless. Suddenly, from the grandstands overlooking the scene, a group of schoolchildren began to chant: "Go Robot! What has long been thought of as a brave new world in which mobile robots freely move about in factories, towns and cities is now approaching. Robots will advance from the dull, dirty and dangerous work that they do today to take on a range of tasks, from rescue work to elder care in close contact with humans. Just as software robots such as Apple's Siri and Microsoft's Cortana have rapidly become useful personal assistants, physical robots will occupy a place in the near future. That is the world imagined by government officials and technologists at the Defense Advanced Research Projects Agency, the American military organization that is charged with the mission of avoiding a Sputnik-style technology threat to national security. Last weekend at the sprawling Los Angeles County Fairgrounds, Darpa concluded the Robotics Challenge, a two-year-long effort to jump start this next generation of smart and presumably helpful robots by offering a cash prize for the designers of a machine that could work in concert with human controllers in a hazardous environment. The $3.5 million competition was won by a South Korean team from the Korean Advanced Institute of Science and Technology. The technology may still seem far-fetched, but betting against the agency that has had a remarkably far-reaching effect on the modern world -- from funding the work that led to both the personal computer and the Internet, to setting expectations that self-driving vehicles are only a matter of years away -- might be a mistake. Darpa officials have taken pains to assure anyone who would listen that it was not primarily interested in designing Terminators, or killer robots. The agency is an arm of the Pentagon, and its futuristic robots are an example of what is described as a "dual use" technology that will have both military and civilian uses. Darpa, which is also known for pioneering the Internet surveillance system that was exposed last year by Edward J. Snowden, has, under its current director, Arati Prabhakar, expanded its watchfulness over the potential effect of the technologies it helps foster. In introducing a workshop for discussion on the effect of robotics held at the end of the challenge competition on Sunday, Dr. Prabhakar described the agency as being committed to a broader mission: "We work together to build the future of robots that can help extend the capabilities that we have and build the technologies that will aid humanity in the future.

A linear function submission-based double-auction (LFS-DA) mechanism for a regional electricity network is proposed in this paper. Each agent in the network is equipped with a battery and a generator. Each agent simultaneously becomes a producer and consumer of electricity, i.e., a prosumer and trades electricity in the regional market at a variable price. In the LFS-DA, each agent uses linear demand and supply functions when they submit bids and asks to an auctioneer in the regional market.The LFS-DA can achieve an exact balance between electricity demand and supply for each time slot throughout the learning phase and was shown capable of solving the primal problem of maximizing the social welfare of the network without any central price setter, e.g., a utility or a large electricity company, in contrast with conventional real-time pricing (RTP). This paper presents a clarification of the relationship between the RTP algorithm derived on the basis of a dual decomposition framework and LFS-DA. Specifically, we proved that the changes in the price profile of the LFS-DA mechanism are equal to those achieved by the RTP mechanism derived from the dual decomposition framework except for a constant factor.

A fundamental limitation of the common machine learning methods is the cost incurred by the preparation of the large training samples required for good generalization. Multi-task learning (MTL) offers a potential remedy. Unlike common single task learning, MTL accomplishes tasks simultaneously with other related tasks, using a shared representation. One general assumption of multi-task learning is that all tasks should share some common structures, including a similarity metric matrix [3], a low ranksubspace [4, 5], parametersofBayesianmodels [6] oracommon set of features [7, 8, 9]. Improved generalization is achieved because what is learned from each task can help with the learning of other tasks [10]. MTL has been successfully applied to many applications such as stock selection [3], speech classification [11] and medical diagnoses [12]. While the majority of existing multi-task feature learning algorithms assume that the relevant features are shared by all tasks, some studies have begun to consider a more general case where features can be commonly shared only among most, but not necessarily all of them. In other word, they try to learn the features specific to each task as well as the common features shared among tasks [1]. In addition, MTL is commonly formulated as a convex regularization problem.

Due to rapid advancement in high-throughput techniques, such as microarrays and next generation sequencing technologies, biological data are increasing exponentially. The current challenge in computational biology and bioinformatics research is how to analyze these huge raw biological data to extract biologically meaningful knowledge. This review paper presents the applications of formal concept analysis for the analysis and knowledge discovery from biological data, including gene expression discretization, gene co-expression mining, gene expression clustering, finding genes in gene regulatory networks, enzyme/protein classifications, binding site classifications, and so on. It also presents a list of FCA-based software tools applied in biological domain and covers the challenges faced so far.

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop. It regularises the weights by minimising a compression cost, known as the variational free energy or the expected lower bound on the marginal likelihood. We show that this principled kind of regularisation yields comparable performance to dropout on MNIST classification. We then demonstrate how the learnt uncertainty in the weights can be used to improve generalisation in non-linear regression problems, and how this weight uncertainty can be used to drive the exploration-exploitation trade-off in reinforcement learning.

Recently, several researchers have brought forth the benefits of searching with multiple (and possibly inadmissible) heuristics, arguing how different heuristics could be independently useful in different parts of the state space. However, algorithms that use inadmissible heuristics in the traditional best-first sense, such as the recently developed Multi-Heuristic A* (MHA*), are subject to a crippling calibration problem: they prioritize nodes for expansion by additively combining the cost-to-come and the inadmissible heuristics even if those heuristics have no connection with the cost-to-go (e.g., the heuristics are uncalibrated) . For instance, if the inadmissible heuristic were an order of magnitude greater than the perfect heuristic, an algorithm like MHA* would simply reduce to a weighted A* search with one consistent heuristic. In this work, we introduce a general multi-heuristic search framework that solves the calibration problem and as a result a) facilitates the effective use of multiple uncalibrated inadmissible heuristics, and b) provides significantly better performance than MHA* whenever tighter sub-optimality bounds on solution quality are desired. Experimental evaluations on a complex full-body robotics motion planning problem and large sliding tile puzzles demonstrate the benefits of our framework.

This paper provides a novel POMDP planning method, called Palm LEAf SEarch (PLEASE), which allows the selection of more than one outcome when their potential impacts are close to the highest one during its forward exploration. Compared with existing trial-based algorithms, PLEASE can save considerable time to propagate the bound improvements of beliefs in deep levels of the search tree to the root belief because of fewer backup operations. Experiments showed that PLEASE scales up SARSOP, one of the fastest algorithms, by orders of magnitude on some POMDP tasks with large observation spaces.

Vehicle sharing (ex: bike sharing, car sharing) systems, an attractive alternative of private transportation, are widely adopted in major cities around the world. In vehicle-sharing systems, base stations (ex: docking stations for bikes) are strategically placed throughout a city and each of the base stations contain a pre-determined number of vehicles at the beginning of each day. Due to the stochastic and individualistic movement of customers, there is typically either congestion (more than required) or starvation (fewer than required) of vehicles at certain base stations, which causes a significant loss in demand. We propose to dynamically redeploy idle vehicles using carriers so as to minimize lost demand or alternatively maximize revenue for the vehicle sharing company. To that end, we contribute an optimization formulation to jointly address the redeployment (of vehicles) and routing (of carriers) problems and provide two approaches that rely on decomposability and abstraction of problem domains to reduce the computation time significantly.

Conflict-Based Search (CBS) and its generalization, Meta-Agent CBS are amongst the strongest newly introduced algorithms for Multi-Agent Path Finding. This paper introduces ICBS, an improved version of CBS. ICBS incorporates three orthogonal improvements to CBS which are systematically described and studied. Experimental results show that each of these improvements reduces the runtime over basic CBS by up to 20x in many cases. When all three improvements are combined, an even larger improvement is achieved, producing state-ofthe art results for a number of domains.

This paper describes a system that automatically transforms a PDDL encoding, calls a planner to solve the transformed representation, and translates the solution back into the original representation. The approach involves counting objects that are indistinguishable, rather than treating them as individuals, which eliminates some unnecessary combinatorial explosion.