Related papers: One Subgoal at a Time: Zero-Shot Generalization to…

Safety comes first in many real-world applications involving autonomous agents. Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those…

Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However,…

Offline reinforcement learning (RL) offers a promising framework for training agents using pre-collected datasets without the need for further environment interaction. However, policies trained on offline data often struggle to generalise…

Generalised zero-shot learning (GZSL) is a classification problem where the learning stage relies on a set of seen visual classes and the inference stage aims to identify both the seen visual classes and a new set of unseen visual classes.…

Context: Requirements engineering researchers have been experimenting with machine learning and deep learning approaches for a range of RE tasks, such as requirements classification, requirements tracing, ambiguity detection, and modelling.…

We study zero-shot generalization in reinforcement learning-optimizing a policy on a set of training tasks to perform well on a similar but unseen test task. To mitigate overfitting, previous work explored different notions of invariance to…

Large language models (LLMs) struggle with precise length control, particularly in zero-shot settings. We conduct a comprehensive study evaluating LLMs' length control capabilities across multiple measures and propose practical methods to…

Many AI problems, in robotics and other domains, are goal-based, essentially seeking trajectories leading to various goal states. Reinforcement learning (RL), building on Bellman's optimality equation, naturally optimizes for a single goal,…

We present a comprehensive system for addressing Tasks A, B, and C of the LLMs4OL 2025 challenge, which together span the full ontology construction pipeline: term extraction, typing, and taxonomy discovery. Our approach combines…

In this study, we address the challenge of learning generalizable policies for compositional tasks defined by logical specifications. These tasks consist of multiple temporally extended sub-tasks. Due to the sub-task inter-dependencies and…

Long-term planning in complex, text-based environments presents significant challenges due to open-ended action spaces, ambiguous observations, and sparse feedback. Recent research suggests that large language models (LLMs) encode rich…

Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite label space for…

Techniques based on Reinforcement Learning (RL) are increasingly being used to design control policies for robotic systems. RL fundamentally relies on state-based reward functions to encode desired behavior of the robot and bad reward…

Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) proposes one solution to this problem. ZSL trains a model…

We aim to solve the problem of temporal-constraint learning from demonstrations to reproduce demonstration-like logic-constrained behaviors. Learning logic constraints is challenging due to the combinatorially large space of possible…

Recent advancements in reinforcement learning have made significant impacts across various domains, yet they often struggle in complex multi-agent environments due to issues like algorithm instability, low sampling efficiency, and the…

Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…

Audio-visual generalised zero-shot learning for video classification requires understanding the relations between the audio and visual information in order to be able to recognise samples from novel, previously unseen classes at test time.…

In many multirobot applications, planning trajectories in a way to guarantee that the collective behavior of the robots satisfies a certain high-level specification is crucial. Motivated by this problem, we introduce counting temporal…

Zero-shot reinforcement learning (RL) methods aim at instantly producing a behavior for an RL task in a given environment, from a description of the reward function. These methods are usually tested by evaluating their average performance…