Reinforcement learning algorithms can be used to optimally solve dynamic decision-making and control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as neural networks or basis function expansions, have two main drawbacks: they are black-box models offering no insight in the mappings learned, and they require significant trial and error tuning of their meta-parameters. In this paper, we propose a new approach to constructing smooth value functions by means of symbolic regression. We introduce three off-line methods for finding value functions based on a state transition model: symbolic value iteration, symbolic policy iteration, and a direct solution of the Bellman equation. The methods are illustrated on four nonlinear control problems: velocity control under friction, one-link and two-link pendulum swing-up, and magnetic manipulation. The results show that the value functions not only yield well-performing policies, but also are compact, human-readable and mathematically tractable. This makes them potentially suitable for further analysis of the closed-loop system. A comparison with alternative approaches using neural networks shows that our method constructs well-performing value functions with substantially fewer parameters.

Facebook rushed to pull down footage of the New Zealand mass shooter's video from its platform, but it didn't start doing so until after the live broadcast was done. In a new post, Facebook VP of Integrity Guy Rosen discussed the company's successes and shortcomings in addressing the situation, as well as its plans to prevent videos like that from spreading on the social network in the future. He explained that while the platform's AI can quickly detect videos containing suicidal or harmful acts, the shooter's stream didn't trigger it. To be able to train the matching AI to detect that specific type of content, the platform needs big volumes of training data. As Facebook explains, something like that is difficult to obtain as "these events are thankfully rare."

Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and they have their own advantages and difficulties. Rule-based reasoning is accurate and explainable but rule learning with searching over the graph always suffers from efficiency due to huge search space. Embedding-based reasoning is more scalable and efficient as the reasoning is conducted via computation between embeddings, but it has difficulty learning good representations for sparse entities because a good embedding relies heavily on data richness. Based on this observation, in this paper we explore how embedding and rule learning can be combined together and complement each other's difficulties with their advantages. We propose a novel framework IterE iteratively learning embeddings and rules, in which rules are learned from embeddings with proper pruning strategy and embeddings are learned from existing triples and new triples inferred by rules. Evaluations on embedding qualities of IterE show that rules help improve the quality of sparse entity embeddings and their link prediction results. We also evaluate the efficiency of rule learning and quality of rules from IterE compared with AMIE+, showing that IterE is capable of generating high quality rules more efficiently. Experiments show that iteratively learning embeddings and rules benefit each other during learning and prediction.

This paper proposes using a linear function approximator, rather than a deep neural network (DNN), to bias a Monte Carlo tree search (MCTS) player for general games. This is unlikely to match the potential raw playing strength of DNNs, but has advantages in terms of generality, interpretability and resources (time and hardware) required for training. Features describing local patterns are used as inputs. The features are formulated in such a way that they are easily interpretable and applicable to a wide range of general games, and might encode simple local strategies. We gradually create new features during the same self-play training process used to learn feature weights. We evaluate the playing strength of an MCTS player biased by learnt features against a standard upper confidence bounds for trees (UCT) player in multiple different board games, and demonstrate significantly improved playing strength in the majority of them after a small number of self-play training games.

A logic program with function symbols is called finitely ground if there is a finite propositional logic program whose stable models are exactly the same as the stable models of this program. Finite groundability is an important property for logic programs with function symbols because it makes feasible to compute such programs' stable models using traditional ASP solvers. In this paper, we introduce new decidable classes of finitely ground programs called poly-bounded and k-EXP-bounded programs, which, to the best of our knowledge, strictly contain all other decidable classes of finitely ground programs discovered so far in the literature. We also study the relevant complexity properties for these classes of programs. We prove that the membership complexities for poly-bounded and k-EXP-bounded programs are EXPTIME-complete and (k+1)-EXPTIME-complete, respectively.

The paper is a half-way between the agent technology and the mathematical reasoning to model tactical decision making tasks. These models are applied to air defense (AD) domain for command and control (C2). It also addresses the issues related to evaluation of agents. The agents are designed and implemented using the agent-programming paradigm. The agents are deployed in an air combat simulated environment for performing the tasks of C2 like electronic counter counter measures, threat assessment, and weapon allocation. The simulated AD system runs without any human intervention, and represents state-of-the-art model for C2 autonomy. The use of agents as autonomous decision making entities is particularly useful in view of futuristic network centric warfare.

Electroencephalograms (EEG) are often contaminated by artifacts which make interpreting them more challenging for clinicians. Hence, automated artifact recognition systems have the potential to aid the clinical workflow. In this abstract, we share the first results on applying various machine learning algorithms to the recently released world's largest open-source artifact recognition dataset. We envision that these results will serve as a benchmark for researchers who might work with this dataset in future. Introduction Removal of artifacts from electroencephalogram (EEG) is a necessary step in analyzing EEG signals since artifacts can lead to severe misinterpretation of these signals. However, manual removal of artifacts requires trained clinicians or neurophysiologists and is a procedure that is known to be both time and resource hungry.

Systems that can automatically analyze EEG signals can aid neurologists by reducing heavy workload and delays. However, such systems need to be first trained using a labeled dataset. While large corpuses of EEG data exist, a fraction of them are labeled. Hand-labeling data increases workload for the very neurologists we try to aid. This paper proposes a semi-supervised learning algorithm that can not only extract meaningful information from large unlabeled EEG datasets but also perform task-specific learning on labeled datasets as small as 5 examples. Introduction Brain-related disorders such as epilepsy can be diagnosed by analyzing electroencephalograms (EEGs).

It's not a perfect measure, but unit sales of industrial robots give some idea of a country's industrial might. The names of the top five buyers in 2017 – China, Japan, South Korea, the US and Germany – shouldn't be too surprising. The global average is 74 per 10,000. One factor in this is the small electronics and automotive sectors here, which are two major drivers of industrial robot investment. The high number of SME and micro-businesses in Australian manufacturing is another.

We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, in which case the existing QA methods fail due to lack of scalability. To tackle this problem, we propose a novel end-to-end reading comprehension method, which we refer to as Episodic Memory Reader (EMR) that sequentially reads the input contexts into an external memory, while replacing memories that are less important for answering unseen questions. Specifically, we train an RL agent to replace a memory entry when the memory is full in order to maximize its QA accuracy at a future timepoint, while encoding the external memory using the transformer architecture to learn representations that considers relative importance between the memory entries. We validate our model on a real-world large-scale textual QA task (TriviaQA) and a video QA task (TVQA), on which it achieves significant improvements over rule-based memory scheduling policies or an RL-based baseline that learns the query-specific importance of each memory independently.