Inverse Constrained Reinforcement Learning (ICRL) is an established field of policy learning that augments reward-driven exploratory optimisation with example-driven constraint inference aimed at exploiting limited observations of expert behaviour. This paper proposes a generalisation of ICRL that employs weighted constraints to better support lifelong learning and to handle domains with potentially conflicting social norms. We introduce a Neuro-Symbolic ICRL approach (NSICRL) with two key components: a symbolic system based on Inductive Logic Programming (ILP) that infers first-order constraints which are human-interpretable and generalise across environment configurations; and a neural system based on Deep Q learning (DQL) that efficiently learns near-optimal policies subject to those constraints. By weighting the high-level ILP constraints (based on the order in which they are learnt) and encoding them as low-level state-action penalties in the DQL reward function, we effectively allow earlier constraints to be overridden by later ones. Unlike prior work in ICRL, our approach is able to continue working when exposed to newly encountered expert behaviours that reveal more nuanced exceptions to previously learnt constraints. We evaluate NSICRL in a simulated traffic domain, which shows how it outperforms existing methods in terms of efficiency and accuracy when learning hard constraints; and which also shows the utility of learning defeasible norms in an ICRL context. To the best of our knowledge, this is the first approach that places equal emphasis on exploratory and imitative learning while also being able to infer defeasible norms in an interpretable way that scales to non-trivial examples.

This paper introduces a method called SUmmarisation with Majority Opinion (SUMO) that integrates and extends two prior approaches for abstractively and extractively summarising UK House of Lords cases. We show how combining two previously distinct lines of work allows us to better address the challenges resulting from this court’s unusual tradition of publishing the opinions of multiple judges with no formal statement of the reasoning (if any) agreed by a majority. We do this by applying natural language processing and machine learning, Conditional Random Fields (CRFs), to a data set we created by fusing together expert-annotated sentence labels from the HOLJ corpus of rhetorical role summary relevance with the ASMO corpus of agreement statement and majority opinion. By using CRFs and a bespoke summary generator on our enriched data set, we show a significant quantitative F1-score improvement in rhetorical role and relevance classification of 10–15% over the state-of-the-art SUM system; and we show a significant qualitative improvement in the quality of our summaries, which closely resemble gold-standard multi-judge abstracts according to a proof-of-principle user study.

This paper is concerned with the task of finding majority opinion (MO) in UK House of Lords (UKHL) case law by analysing agreement statements (AS) that explicitly express the appointed judges' acceptance of each other's reasoning. We introduce a corpus of 300 UKHL cases in which the relevant AS and MO have been annotated by three legal experts; and we introduce an AI system that automatically identifies this AS and MO with a performance comparable to humans.

Abstract This paper introduces a new logic-based method for optimising the selection of compiler flags on embedded architectures. In particular, we use Inductive Logic Programming (ILP) to learn logical rules that relate effective compiler flags to specific program features. Unlike earlier work, we aim to infer human-readable rules and we seek to develop a relational first-order approach which automatically discovers relevant features rather than relying on a vector of predetermined attributes. To this end we generated a data set by measuring execution times of 60 benchmarks on an embedded system development board and we developed an ILP prototype which outperforms the current state-of-the-art learning approach in 34 of the 60 benchmarks. Finally, we combined the strengths of the current state of the art and our ILP method in a hybrid approach which reduced execution times by an average of 8% and up to 50% in some cases.

This paper applies the logic-based formalism of Answer Set Programming (ASP) to the modelling of competition, inhibition and cycles in biochemical networks. In particular, it introduces a generic framework that unifies the competitive and inhibitory mechanisms proposed in the literature along with their complementary approaches to reasoning about loops. We show how the nonmonotonic effects of competition and inhibition can be naturally encoded in the formalism of ASP and that the different ways of handling loops correspond to the computation of stable and supported models. We also show that inhibitory models are currently more general than competitive models and we argue that that both interpretations of loops are justified in some applications.

This paper presents a qualitative logic-based method for the steady-state analysis and revision of metabolic networks with inhibition. The approach is able to automatically revise an initial metabolic model - through the addition and removal of whole reactions or individual substrates, products and inhibitors - in order to ensure the existence of a steady-state behaviour consistent with a set of experimental observations. We show how this can be done in a nonmonotonic logic programming setting and discuss the challenges that arise when metabolic cycles or mutual inhibitions occur in the underlying network.

This paper describes a new logic-based approach for representing and reasoning about metabolic networks.First it shows how biological pathways can be elegantly represented in a logic programming formalism able to model full chemical reactions with substrates and products in different cell compartments, and which are catalysed by iso-enzymes or enzyme-complexes that are subject to inhibitory feedbacks.Then it shows how a nonmonotonic reasoning system called XHAIL can be used as a practical method for learning and revising such metabolic networks from observational data. Preliminary results are described in which the approach is validated on a state-of-the-art model of aromatic amino acid biosynthesis.

Techniques for detecting synthetic lethal mutations in double gene deletion experiments are emerging as powerful tool for analysing genes in parallel or overlapping pathways with a shared function. This paper introduces a logic-based approach that uses synthetic lethal mutations for mapping genes of unknown function to enzymes in a known metabolic network. We show how such mappings can be automatically computed by a logical learning system called eXtended Hybrid Abductive Inductive Learning (XHAIL).