Journal of Artificial Intelligence Research


Blind Spot Detection for Safe Sim-to-Real Transfer

Journal of Artificial Intelligence Research

Agents trained in simulation may make errors when performing actions in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult for the agent to discover because the agent is unable to predict them a priori. In this work, we propose the use of oracle feedback to learn a predictive model of these blind spots in order to reduce costly errors in real-world applications. We focus on blind spots in reinforcement learning (RL) that occur due to incomplete state representation: when the agent lacks necessary features to represent the true state of the world, and thus cannot distinguish between numerous states. Our system learns models for predicting blind spots within unseen regions of the state space by combining techniques for label aggregation, calibration, and supervised learning.


Planning for Hybrid Systems via Satisfiability Modulo Theories

Journal of Artificial Intelligence Research

Planning for hybrid systems is important for dealing with real-world applications, and PDDL supports this representation of domains with mixed discrete and continuous dynamics. In this paper we present a new approach for planning for hybrid systems, based on encoding the planning problem as a Satisfiability Modulo Theories (SMT) formula. This is the first SMT encoding that can handle the whole set of PDDL features (including processes and events), and is implemented in the planner SMTPlan. SMTPlan not only covers the full semantics of PDDL, but can also deal with non-linear polynomial continuous change without discretization. This allows it to generate plans with non-linear dynamics that are correct-by-construction.


TensorLog: A Probabilistic Database Implemented Using Deep-Learning Infrastructure

Journal of Artificial Intelligence Research

We present an implementation of a probabilistic first-order logic called TensorLog, in which classes of logical queries are compiled into differentiable functions in a neural-network infrastructure such as Tensorflow or Theano. This leads to a close integration of probabilistic logical reasoning with deep-learning infrastructure: in particular, it enables high-performance deep learning frameworks to be used for tuning the parameters of a probabilistic logic. The integration with these frameworks enables use of GPU-based parallel processors for inference and learning, making TensorLog the first highly parallellizable probabilistic logic. Experimental results show that TensorLog scales to problems involving hundreds of thousands of knowledge-base triples and tens of thousands of examples.


Jointly Improving Parsing and Perception for Natural Language Commands through Human-Robot Dialog

Journal of Artificial Intelligence Research

In this work, we present methods for using human-robot dialog to improve language understanding for a mobile robot agent. The agent parses natural language to underlying semantic meanings and uses robotic sensors to create multi-modal models of perceptual concepts like red and heavy. The agent can be used for showing navigation routes, delivering objects to people, and relocating objects from one location to another. The agent employs opportunistic active learning to select questions about how words relate to objects, improving its understanding of perceptual concepts. We evaluated this agent on Amazon Mechanical Turk.


Adversarial Attacks on Crowdsourcing Quality Control

Journal of Artificial Intelligence Research

Crowdsourcing is a popular methodology to collect manual labels at scale. Such labels are often used to train AI models and, thus, quality control is a key aspect in the process. One of the most popular quality assurance mechanisms in paid micro-task crowdsourcing is based on gold questions: the use of a small set of tasks of which the requester knows the correct answer and, thus, is able to directly assess crowd work quality. In this paper, we show that such mechanism is prone to an attack carried out by a group of colluding crowd workers that is easy to implement and deploy: the inherent size limit of the gold set can be exploited by building an inferential system to detect which parts of the job are more likely to be gold questions. The described attack is robust to various forms of randomisation and programmatic generation of gold questions.


Best-First Enumeration Based on Bounding Conflicts, and its Application to Large-scale Hybrid Estimation

Journal of Artificial Intelligence Research

There is an increasing desire for autonomous systems to have high levels of robustness and safety, attained through continuously planning and self-repairing online. Underlying this is the need to accurately estimate the system state and diagnose subtle failures. Estimation methods based on hybrid discrete and continuous state models have emerged as a method of precisely computing these estimates. However, existing methods have difficulty scaling to systems with more than a handful of components. Discrete, consistency based state estimation capabilities can scale to this level by combining best-first enumeration and conflict-directed search.


The Impact of Treewidth on Grounding and Solving of Answer Set Programs

Journal of Artificial Intelligence Research

In this paper, we aim to study how the performance of modern answer set programming (ASP) solvers is influenced by the treewidth of the input program and to investigate the consequences of this relationship. We first perform an experimental evaluation that shows that the solving performance is heavily influenced by treewidth, given ground input programs that are otherwise uniform, both in size and construction. This observation leads to an important question for ASP, namely, how to design encodings such that the treewidth of the resulting ground program remains small. To this end, we study two classes of disjunctive programs, namely guarded and connection-guarded programs. In order to investigate these classes, we formalize the grounding process using MSO transductions.


The 2 k Neighborhoods for Grid Path Planning

Journal of Artificial Intelligence Research

Grid path planning is an important problem in AI. Its understanding has been key for the development of autonomous navigation systems. An interesting and rather surprising fact about the vast literature on this problem is that only a few neighborhoods have been used when evaluating these algorithms. Indeed, only the 4- and 8-neighborhoods are usually considered, and rarely the 16-neighborhood. This paper describes three contributions that enable the construction of effective grid path planners for extended 2k-neighborhoods; that is, neighborhoods that admit 2k neighbors per state, where k is a parameter.


Regret Bounds for Reinforcement Learning via Markov Chain Concentration

Journal of Artificial Intelligence Research

We give a simple optimistic algorithm for which it is easy to derive regret bounds of O(sqrt{t-mix SAT}) steps in uniformly ergodic Markov decision processes with S states, A actions, and mixing time parameter t-mix. These bounds are the first regret bounds in the general, non-episodic setting with an optimal dependence on all given parameters. They could only be improved by using an alternative mixing time parameter.


The Force Awakens: Artificial Intelligence for Consumer Law

Journal of Artificial Intelligence Research

Recent years have been tainted by market practices that continuously expose us, as consumers, to new risks and threats. We have become accustomed, and sometimes even resigned, to businesses monitoring our activities, examining our data, and even meddling with our choices. Artificial Intelligence (AI) is often depicted as a weapon in the hands of businesses and blamed for allowing this to happen. In this paper, we envision a paradigm shift, where AI technologies are brought to the side of consumers and their organizations, with the aim of building an efficient and effective counter-power. AI-powered tools can support a massive-scale automated analysis of textual and audiovisual data, as well as code, for the benefit of consumers and their organizations.