As more and more data is being generated by sensor networks, social media and organizations, the Web interlinking this wealth of information becomes more complex. This is particularly true for the so-called Web of Data, in which data is semantically enriched and interlinked using ontologies. In this large and uncoordinated environment, reasoning can be used to check the consistency of the data and of associated ontologies, or to infer logical consequences which, in turn, can be used to obtain new insights from the data. However, reasoning approaches need to be scalable in order to enable reasoning over the entire Web of Data. To address this problem, several high-performance reasoning systems, which mainly implement distributed or parallel algorithms, have been proposed in the last few years. These systems differ significantly; for instance in terms of reasoning expressivity, computational properties such as completeness, or reasoning objectives. In order to provide a first complete overview of the field, this paper reports a systematic review of such scalable reasoning approaches over various ontological languages, reporting details about the methods and over the conducted experiments. We highlight the shortcomings of these approaches and discuss some of the open problems related to performing scalable reasoning.

Reinforcement learning (RL) algorithms are often used to compute agents capable of acting in environments without prior knowledge of the environment dynamics. However, these algorithms struggle to converge in environments with large branching factors and their large resulting state-spaces. In this work, we develop an approach to compress the number of entries in a Q-value table using a deep auto-encoder. We develop a set of techniques to mitigate the large branching factor problem. We present the application of such techniques in the scenario of a real-time strategy (RTS) game, where both state space and branching factor are a problem. We empirically evaluate an implementation of the technique to control agents in an RTS game scenario where classical RL fails and provide a number of possible avenues of further work on this problem.

The majority of multi-agent reinforcement learning (MARL) implementations aim to optimize systems with respect to a single objective, despite the fact that many real-world problems are inherently multi-objective in nature. Research into multi-objective MARL is still in its infancy, and few studies to date have dealt with the issue of credit assignment. Reward shaping has been proposed as a means to address the credit assignment problem in single-objective MARL, however it has been shown to alter the intended goals of a domain if misused, leading to unintended behaviour. Two popular shaping methods are potential-based reward shaping and difference rewards, and both have been repeatedly shown to improve learning speed and the quality of joint policies learned by agents in single-objective MARL domains. This work discusses the theoretical implications of applying these shaping approaches to cooperative multi-objective MARL problems, and evaluates their efficacy using two benchmark domains. Our results constitute the first empirical evidence that agents using these shaping methodologies can sample true Pareto optimal solutions in cooperative multi-objective stochastic games.

We consider task planning for long-living intelligent agents situated in dynamic environments. Specifically, we address the problem of incomplete knowledge of the world due to the addition of new objects with unknown action models. We propose a multilayered agent architecture that uses meta-reasoning to control hierarchical task planning and situated learning, monitor expectations generated by a plan against world observations, forms goals and rewards for the situated reinforcement learner, and learns the missing planning knowledge relevant to the new objects. We use occupancy grids as a low-level representation for the high-level expectations to capture changes in the physical world due to the additional objects, and provide a similarity method for detecting discrepancies between the expectations and the observations at run-time; the meta-reasoner uses these discrepancies to formulate goals and rewards for the learner, and the learned policies are added to the hierarchical task network plan library for future re-use. We describe our experiments in the Minecraft and Gazebo microworlds to demonstrate the efficacy of the architecture and the technique for learning. We test our approach against an ablated reinforcement learning (RL) version, and our results indicate this form of expectation enhances the learning curve for RL while being more generic than propositional representations.

The concept of a norm is found widely across fields including artificial intelligence, biology, computer security, cultural studies, economics, law, organizational behaviour and psychology. The concept is studied with different terminology and perspectives, including individual, social, legal and philosophical. If a norm is an expected behaviour in a social setting, then this article considers how it can be determined whether an individual is adhering to this expected behaviour. We call this process monitoring, and again it is a concept known with different terminology in different fields. Monitoring of norms is foundational for processes of accountability, enforcement, regulation and sanctioning. Starting with a broad focus and narrowing to the multi-agent systems literature, this survey addresses four key questions: what is monitoring, what is monitored, who does the monitoring and how the monitoring is accomplished.