Luke Dickens

JAIR Journal 2025 Journal Article

A Graphical Formalism for Reasoning about Substitution in Resource Transforming Procedures

• Antonis Bikakis
• Fabio Aurelio D'Asaro
• Aissatou Diallo
• Luke Dickens
• Anthony Hunter
• Rob Miller

The ability to repurpose and substitute materials and resources when necessary is an important aspect of human reasoning and activity. In particular, substitution plays a vital role in resource consuming and artifact producing activities – purposeful, goal directed procedures that transform resources from raw materials into finished products, the descriptions of which we refer to here as recipes. To see this, consider how adaptable humans are when we encounter constraints, such as limited resources, when making, manufacturing and constructing. In spite of this there has been comparatively little work given to developing representations for substitution within such contexts in a formal reasoning framework. We address this gap by proposing a graphical formalisation that captures consumables and the actions on them in the form of labelled bipartite graphs. Using examples such as “do it yourself" (DIY) instructions, manufacturing processes and cooking recipes to illustrate, we then propose formal definitions for comparing recipes, for composing recipes from subrecipes, and for deconstructing recipes into subrecipes. We then introduce and compare two formal definitions for substitution which are required when there are missing consumables, or some actions are not possible, or because there is some need to change the final product. We illustrate how automated reasoning about recipes in this context may be achieved by implementing our definitions in answer set programming (ASP).

TIME Conference 2025 Conference Paper

A Translation of Probabilistic Event Calculus into Markov Decision Processes (Short Paper)

• Lyris Xu
• Fabio Aurelio D'Asaro
• Luke Dickens

Probabilistic Event Calculus (PEC) is a logical framework for reasoning about actions and their effects in uncertain environments, which enables the representation of probabilistic narratives and computation of temporal projections. The PEC formalism offers significant advantages in interpretability and expressiveness for narrative reasoning. However, it lacks mechanisms for goal-directed reasoning. Our work bridges this gap by developing a formal translation of PEC domains into Markov Decision Processes (MDPs), introducing the concept of "action-taking situations" to preserve PEC’s flexible action semantics. The resulting PEC-MDP formalism enables the extensive collection of algorithms and theoretical tools developed for MDPs to be applied to PEC’s interpretable narrative domains. We demonstrate how the translation supports both temporal reasoning tasks and objective-driven planning, with methods for mapping learned policies back into human-readable PEC representations, maintaining interpretability while extending PEC’s capabilities.

NeSy Conference 2025 Conference Paper

Disentangling Neural Disjunctive Normal Form Models

• Kexin Gu Baugh
• Vincent Perreault
• Matthew Baugh
• Luke Dickens
• Katsumi Inoue
• Alessandra Russo

Neural Disjunctive Normal Form (DNF) based models are powerful and interpretable approaches to neuro-symbolic learning and have shown promising results in classification and reinforcement learning settings without prior knowledge of the tasks. However, their performance is degraded by the thresholding of the post-training symbolic translation process. We show here that part of the performance degradation during translation is due to its failure to disentangle the learned knowledge represented in the form of the networks’ weights. We address this issue by proposing a new disentanglement method; by splitting nodes that encode nested rules into smaller independent nodes, we are able to better preserve the models’ performance. Through experiments on binary, multiclass, and multilabel classification tasks (including those requiring predicate invention), we demonstrate that our disentanglement method provides compact and interpretable logical representations for the neural DNF-based models, with performance closer to that of their pre-translation counterparts. Our code is available at https: //github. com/kittykg/disentangling-ndnf-classification.

AAAI Conference 2025 Conference Paper

Measuring Error Alignment for Decision-Making Systems

• Binxia Xu
• Antonis Bikakis
• Daniel F.O. Onah
• Andreas Vlachidis
• Luke Dickens

Given that AI systems are set to play a pivotal role in future decision-making processes, their trustworthiness and reliability are of critical concern. Due to their scale and complexity, modern AI systems resist direct interpretation, and alternative ways are needed to establish trust in those systems, and determine how well they align with human values. We argue that good measures of the information processing similarities between AI and humans, may be able to achieve these same ends. While Representational alignment (RA) approaches measure similarity between the internal states of two systems, the associated data can be expensive and difficult to collect for human systems. In contrast, Behavioural alignment (BA) comparisons are cheaper and easier, but questions remain as to their sensitivity and reliability. We propose two new behavioural alignment metrics misclassification agreement which measures the similarity between the errors of two systems on the same instances, and class-level error similarity which measures the similarity between the error distributions of two systems. We show that our metrics correlate well with RA metrics, and provide complementary information to another BA metric, within a range of domains, and set the scene for a new approach to value alignment.

AAMAS Conference 2025 Conference Paper

Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies

• Kexin Gu Baugh
• Luke Dickens
• Alessandra Russo

Although deep reinforcement learning has been shown to be effective, the model’s black-box nature presents barriers to direct policy interpretation. To address this problem, we propose a neurosymbolic approach called neural DNF-MT for end-to-end policy learning. The differentiable nature of the neural DNF-MT model enables the use of deep actor-critic algorithms for training. At the same time, its architecture is designed so that trained models can be directly translated into interpretable policies expressed as standard (bivalent or probabilistic) logic programs. Moreover, additional layers can be included to extract abstract features from complex observations, acting as a form of predicate invention. The logic representations are highly interpretable, and we show how the bivalent representations of deterministic policies can be edited and incorporated back into a neural model, facilitating manual intervention and adaptation of learned policies. We evaluate our approach on a range of tasks requiring learning deterministic or stochastic behaviours from various forms of observations. Our empirical results show that our neural DNF-MT model performs at the level of competing black-box methods whilst providing interpretable policies.

ECAI Conference 2025 Conference Paper

RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation

• Aïssatou Diallo
• Antonis Bikakis
• Luke Dickens
• Anthony Hunter
• Rob Miller 0002

Commonsense reasoning is a key aspect of human intelligence. If we are to develop robust and deep intelligent systems, then we need to understand the diversity and complexity of commonsense reasoning across the gamut of human activities. An interesting class of commonsense reasoning problems arises when people are faced with natural disasters. To investigate this topic, we present RESPONSE, a human-curated dataset containing 1789 annotated instances featuring 6037 sets of questions designed to assess LLMs’ commonsense reasoning in disaster situations across different time frames. The dataset includes problem descriptions, missing resources, time-sensitive solutions, and their justifications, with a subset validated by environmental engineers. Through both automatic metrics and human evaluation, we compare LLM-generated recommendations against human responses. Our findings show that even state-of-the-art models like GPT-4 achieve only 37% human-evaluated correctness for immediate response actions, highlighting significant room for improvement in LLMs’ ability for commonsense reasoning in crises.

NeSy Conference 2024 Conference Paper

Context Helps: Integrating Context Information with Videos in a Graph-Based HAR Framework

• Binxia Xu
• Antonis Bikakis
• Daniel F. O. Onah
• Andreas Vlachidis
• Luke Dickens

Abstract Human Activity Recognition (HAR) from videos is a challenging, data intensive task. There have been significant strides in recent years, but even state-of-the-art (SoTA) models rely heavily on domain specific supervised fine-tuning of visual features, and even with this data- and compute-intensive fine-tuning, overall performance can still be limited. We argue that the next generation of HAR models could benefit from explicit neuro-symbolic mechanisms in order to flexibly exploit rich contextual information available in, and for, videos. With a view to this, we propose a Human Activity Recognition with Context Prompt (HARCP) task to investigate the value of contextual information for video-based HAR. We also present a neuro-symbolic graph neural network-based framework that integrates zero-shot object localisation to address the HARCP task. This captures the human activity as a sequence of graph-based scene representations relating parts of the human body to key objects, supporting the targeted injection of external contextual knowledge in symbolic form. We evaluate existing HAR baselines alongside our graph-based methods to demonstrate the advantage of being able to accommodate this additional channel of information. Our evaluations show that not only does context information from key objects boost accuracy beyond that provided by SoTA HAR models alone, there is also a greater semantic similarity between our model’s errors and the target class. We argue that this represents an improved model alignment with human-like errors and quantify this with a novel measure we call Semantic Prediction Dispersion.

NeurIPS Conference 2022 Conference Paper

Formalizing Consistency and Coherence of Representation Learning

• Harald Strömfelt
• Luke Dickens
• Artur Garcez
• Alessandra Russo

In the study of reasoning in neural networks, recent efforts have sought to improve consistency and coherence of sequence models, leading to important developments in the area of neuro-symbolic AI. In symbolic AI, the concepts of consistency and coherence can be defined and verified formally, but for neural networks these definitions are lacking. The provision of such formal definitions is crucial to offer a common basis for the quantitative evaluation and systematic comparison of connectionist, neuro-symbolic and transfer learning approaches. In this paper, we introduce formal definitions of consistency and coherence for neural systems. To illustrate the usefulness of our definitions, we propose a new dynamic relation-decoder model built around the principles of consistency and coherence. We compare our results with several existing relation-decoders using a partial transfer learning task based on a novel data set introduced in this paper. Our experiments show that relation-decoders that maintain consistency over unobserved regions of representation space retaincoherence across domains, whilst achieving better transfer learning performance.

NeSy Conference 2021 Conference Paper

Coherent and Consistent Relational Transfer Learning with Auto-encoders

• Harald Strömfelt
• Luke Dickens
• Artur S. d'Avila Garcez
• Alessandra Russo

Human defined concepts are inherently transferable, but it is not clear under what conditions they can be modelled effectively by non-symbolic artificial learners. This paper argues that for a transferable concept to be learned, the system of relations that define it must be coherent across domains and properties. That is, they should be consistent with respect to relational constraints, and this consistency must extend beyond the representations encountered in the source domain. Further, where relations are modelled by differentiable functions, their gradients must conform – the functions must at times move together to preserve consistency. We propose a Partial Relation Transfer (PRT) task which exposes how well relation-decoders model these properties, and exemplify this with ordinality prediction transfer task, including a new data set for the transfer domain. We evaluate this on existing relation-decoder models, as well as a novel model designed around the principles of consistency and gradient conformity. Results show that consistency across broad regions of input space indicates good transfer performance, and that good gradient conformity facilitates consistency.

AIJ Journal 2020 Journal Article

Probabilistic reasoning about epistemic action narratives

• Fabio Aurelio D'Asaro
• Antonis Bikakis
• Luke Dickens
• Rob Miller

We propose the action language EPEC – Epistemic Probabilistic Event Calculus – that supports probabilistic, epistemic reasoning about narratives of action occurrences and environmentally triggered events, and in particular facilitates reasoning about future belief-conditioned actions and their consequences in domains that include both perfect and imperfect sensing actions. To provide a declarative semantics for sensing and belief conditioned actions in a probabilistic, narrative setting we introduce the novel concept of an epistemic reduct. We then formally compare our language with two established frameworks for probabilistic reasoning about action – the action language PAL by Baral et al. , and the extension of the situation calculus to reason about noisy sensors and effectors by Bacchus et al. In both cases we prove a correspondence with EPEC for a class of domains representable in both frameworks.

ECAI Conference 2010 Conference Paper

The Dynamics of Multi-Agent Reinforcement Learning

• Luke Dickens
• Krysia Broda
• Alessandra Russo

Infinite-horizon multi-agent control processes with non-determinism and partial state knowledge have particularly interesting properties with respect to adaptive control, such as the non-existence of Nash Equilibria (NE) or non-strict NE which are nonetheless points of convergence. The identification of reinforcement learning (RL) algorithms that are robust, accurate and efficient when applied to these general multi-agent domains is an open, challenging problem. This paper uses learning pressure fields as a means for evaluating RL algorithms in the context of multi-agent processes. Specifically, we show how to model partially observable infinite-horizon stochastic processes (single-agent) and games (multi-agent) within the Finite Analytic Stochastic Process framework. Taking long term average expected returns as utility measures, we show the existence of learning pressure fields: vector fields – similar to the dynamics of evolutionary game theory, which indicate medium and long term learning behaviours of agents independently seeking to maximise this utility. We show empirically that these learning pressure fields are followed closely by policy-gradient RL algorithms.

AAAI Conference 2008 Short Paper

Perpetual Learning for Non-Cooperative Multiple Agents

• Luke Dickens