Related papers: LISA: Learning Interpretable Skill Abstractions fr…

Learning analytics have been argued as a key enabler to improving student learning at scale. Yet, despite considerable efforts by the learning analytics community across the world over the past decade, the evidence to support that claim is…

Language is highly structured, with syntactic and semantic structures, to some extent, agreed upon by speakers of the same language. With implicit or explicit awareness of such structures, humans can learn and use language efficiently and…

Current model-based reinforcement learning methods struggle when operating from complex visual scenes due to their inability to prioritize task-relevant features. To mitigate this problem, we propose learning Task Informed Abstractions…

Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language…

We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical variational inference…

Modern Systems-on-Chip (SoC) designs are increasingly heterogeneous and contain specialized semi-programmable accelerators in addition to programmable processors. In contrast to the pre-accelerator era, when the ISA played an important role…

Recent Vision-Language-Action (VLA) models show strong generalization capabilities, yet they lack introspective mechanisms for anticipating failures and requesting help from a human supervisor. We present \textbf{INSIGHT}, a learning…

We present Generalizable Hierarchical Skill Learning (GSL), a novel framework for hierarchical policy learning that significantly improves policy generalization and sample efficiency in robot manipulation. One core idea of GSL is to use…

The use of imitation learning to learn a single policy for a complex task that has multiple modes or hierarchical structure can be challenging. In fact, previous work has shown that when the modes are known, learning separate policies for…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

Vision-language-action models (VLAs) have become an increasingly popular approach for addressing robot manipulation problems in recent years. However, such models need to output actions at a rate suitable for robot control, which limits the…

Effective planning in the real world requires not only world knowledge, but the ability to leverage that knowledge to build the right representation of the task at hand. Decades of hierarchical planning techniques have used domain-specific…

In this paper, we address the discovery of robotic options from demonstrations in an unsupervised manner. Specifically, we present a framework to jointly learn low-level control policies and higher-level policies of how to use them from…

Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…

Inductive Logic Programming (ILP) systems learn generalised, interpretable rules in a data-efficient manner utilising existing background knowledge. However, current ILP systems require training examples to be specified in a structured…

Recent work analyzing in-context learning (ICL) has identified a broad set of strategies that describe model behavior in different experimental conditions. We aim to unify these findings by asking why a model learns these disparate…

Large-scale Transformer language models (LMs) trained solely on next-token prediction with web-scale data can solve a wide range of tasks after seeing just a few examples. The mechanism behind this capability, known as in-context learning…

Reinforcement learning agents can learn to solve sequential decision tasks by interacting with the environment. Human knowledge of how to solve these tasks can be incorporated using imitation learning, where the agent learns to imitate…

Reinforcement Learning (RL) bears the promise of being a game-changer in many applications. However, since most of the literature in the field is currently focused on opaque models, the use of RL in high-stakes scenarios, where…

We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. Instructions are expressed in a well-known formal language -- linear temporal logic (LTL) -- and can specify a…