Therefore, neuro-symbolic RL aims at creating policies that are interpretable in the first place. Unfortunately, interpretability is not explainability. To achieve both, we introduce Neurally gUided Differentiable loGic policiEs (NUDGE).

Therefore, neuro-symbolic RL aims at creating policies that are interpretable in the first place. Unfortunately, interpretability is not explainability. To achieve both, we introduce Neurally gUided Differentiable loGic policiEs (NUDGE).

Existing text representations such as embeddings and bag-of-words are not suitable for rule learning due to their high dimensionality and absent or questionable feature-level interpretability. This article explores whether large language models (LLMs) could address this by extracting a small number of interpretable features from text. We demonstrate this process on two datasets (CORD-19 and M17+) containing several thousand scientific articles from multiple disciplines and a target being a proxy for research impact. An evaluation based on testing for the statistically significant correlation with research impact has shown that LLama 2-generated features are semantically meaningful. We consequently used these generated features in text classification to predict the binary target variable representing the citation rate for the CORD-19 dataset and the ordinal 5-class target representing an expert-awarded grade in the M17+ dataset. Machine-learning models trained on the LLM-generated features provided similar predictive performance to the state-of-the-art embedding model SciBERT for scientific text. The LLM used only 62 features compared to 768 features in SciBERT embeddings, and these features were directly interpretable, corresponding to notions such as article methodological rigor, novelty, or grammatical correctness. As the final step, we extract a small number of well-interpretable action rules. Consistently competitive results obtained with the same LLM feature set across both thematically diverse datasets show that this approach generalizes across domains.

Defect reduction planning plays a vital role in enhancing software quality and minimizing software maintenance costs. By training a black box machine learning model and "explaining" its predictions, explainable AI for software engineering aims to identify the code characteristics that impact maintenance risks. However, post-hoc explanations do not always faithfully reflect what the original model computes. In this paper, we introduce CounterACT, a Counterfactual ACTion rule mining approach that can generate defect reduction plans without black-box models. By leveraging action rules, CounterACT provides a course of action that can be considered as a counterfactual explanation for the class (e.g., buggy or not buggy) assigned to a piece of code. We compare the effectiveness of CounterACT with the original action rule mining algorithm and six established defect reduction approaches on 9 software projects. Our evaluation is based on (a) overlap scores between proposed code changes and actual developer modifications; (b) improvement scores in future releases; and (c) the precision, recall, and F1-score of the plans. Our results show that, compared to competing approaches, CounterACT's explainable plans achieve higher overlap scores at the release level (median 95%) and commit level (median 85.97%), and they offer better trade-off between precision and recall (median F1-score 88.12%). Finally, we venture beyond planning and explore leveraging Large Language models (LLM) for generating code edits from our generated plans. Our results show that suggested LLM code edits supported by our plans are actionable and are more likely to pass relevant test cases than vanilla LLM code recommendations.

We consider several algorithms for exploring and filling an unknown, connected region, by simple, airborne agents. The agents are assumed to be identical, autonomous, anonymous and to have a finite amount of memory. The region is modeled as a connected sub-set of a regular grid composed of square cells. The algorithms described herein are suited for Micro Air Vehicles (MAV) since these air vehicles enable unobstructed views of the ground below and can move freely in space at various heights. The agents explore the region by applying various action-rules based on locally acquired information Some of them may settle in unoccupied cells as the exploration progresses. Settled agents become virtual pheromones for the exploration and coverage process, beacons that subsequently aid the remaining, and still exploring, mobile agents. We introduce a backward propagating information diffusion process as a way to implement a deterministic indicator of process termination and guide the mobile agents. For the proposed algorithms, complete covering of the graph in finite time is guaranteed when the size of the region is fixed. Bounds on the coverage times are also derived. Extensive simulation results exhibit good agreement with the theoretical predictions.

This article describes an action rule induction algorithm based on a sequential covering approach. Two variants of the algorithm are presented. The algorithm allows the action rule induction from a source and a target decision class point of view. The application of rule quality measures enables the induction of action rules that meet various quality criteria. The article also presents a method for recommendation induction. The recommendations indicate the actions to be taken to move a given test example, representing the source class, to the target one. The recommendation method is based on a set of induced action rules. The experimental part of the article presents the results of the algorithm operation on sixteen data sets. As a result of the conducted research the Ac-Rules package was made available.

Creating incentives for cooperation is a challenge in natural and artificial systems. One potential answer is reputation, whereby agents trade the immediate cost of cooperation for the future benefits of having a good reputation. Game theoretical models have shown that specific social norms can make cooperation stable, but how agents can independently learn to establish effective reputation mechanisms on their own is less understood. We use a simple model of reinforcement learning to show that reputation mechanisms generate two coordination problems: agents need to learn how to coordinate on the meaning of existing reputations and collectively agree on a social norm to assign reputations to others based on their behavior. These coordination problems exhibit multiple equilibria, some of which effectively establish cooperation. When we train agents with a standard Q-learning algorithm in an environment with the presence of reputation mechanisms, convergence to undesirable equilibria is widespread. We propose two mechanisms to alleviate this: (i) seeding a proportion of the system with fixed agents that steer others towards good equilibria; and (ii), intrinsic rewards based on the idea of introspection, i.e., augmenting agents' rewards by an amount proportionate to the performance of their own strategy against themselves. A combination of these simple mechanisms is successful in stabilizing cooperation, even in a fully decentralized version of the problem where agents learn to use and assign reputations simultaneously. We show how our results relate to the literature in Evolutionary Game Theory, and discuss implications for artificial, human and hybrid systems, where reputations can be used as a way to establish trust and cooperation.

This paper proposes an approach to analyze an event log of a business process in order to generate case-level recommendations of treatments that maximize the probability of a given outcome. Users classify the attributes in the event log into controllable and non-controllable, where the former correspond to attributes that can be altered during an execution of the process (the possible treatments). We use an action rule mining technique to identify treatments that co-occur with the outcome under some conditions. Since action rules are generated based on correlation rather than causation, we then use a causal machine learning technique, specifically uplift trees, to discover subgroups of cases for which a treatment has a high causal effect on the outcome after adjusting for confounding variables. We test the relevance of this approach using an event log of a loan application process and compare our findings with recommendations manually produced by process mining experts.

A version of the situation calculus in which situations are represented as first-order terms is presented. Fluents can be computed from the term structure, and actions on the situations correspond to rewrite rules on the terms. Actions that only depend on or influence a subset of the fluents can be described as rewrite rules that operate on subterms of the terms in some cases. If actions are bidirectional then efficient completion methods can be used to solve planning problems. This representation for situations and actions is most similar to the fluent calculus of Thielscher \cite{Thielscher98}, except that this representation is more flexible and more use is made of the subterm structure. Some examples are given, and a few general methods for constructing such sets of rewrite rules are presented. This paper was submitted to FSCD 2020 on December 23, 2019.

We develop a qualitative model of decision making with two aims: to describe how people make simple decisions and to enable computer programs to do the same. Current approaches based on Planning or Decisions Theory either ignore uncertainty and tradeoffs, or provide languages and algorithms that are too complex for this task. The proposed model provides a language based on rules, a semantics based on high probabilities and lexicographical preferences, and a transparent decision procedure where reasons for and against decisions interact. The model is no substitude for Decision Theory, yet for decisions that people find easy to explain it may provide an appealing alternative.