20 accepted papers
Model collapse, the degradation in performance that arises when generative models are trained on the outputs of prior models, is an increasing concern as artificially generated content proliferates. Related critiques of large language models have highlighted their tendency to reproduce frequent patt…
We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent approaches have sought to segment trajectories into reusable skills or options, most rely on action labels, rewards, or handcrafted annotations, limiting their appl…
In spite of finite dimension ReLU neural networks being a consistent factor behind recent deep learning successes, a theory of feature learning in these models remains elusive. Currently, insightful theories still rely on assumptions including the linearity of the network computations, unstructured…
This paper presents the Esethu Framework, a sustainable data curation framework specifically designed to empower local communities and ensure equitable benefit-sharing from their linguistic resource. This framework is supported by the Esethu license, a novel community-centric data license. As a proo…
It is desirable for an agent to be able to solve a rich variety of problems that can be specified through language in the same environment. A popular approach towards obtaining such agents is to reuse skills learned in prior tasks to generalise compositionally to new ones. However, this is a challen…
The disparity in the languages commonly studied in Natural Language Processing (NLP) is typically reflected by referring to languages as low vs high-resourced. However, there is limited consensus on what exactly qualifies as a ‘low-resource language.’ To understand how NLP papers define and study ‘l…
While reinforcement learning has achieved remarkable successes in several domains, its real-world application is limited due to many methods failing to generalise to unfamiliar conditions. In this work, we consider the problem of generalising to new transition dynamics, corresponding to cases in whi…
A number of machine learning models have been proposed with the goal of achieving systematic generalization: the ability to reason about new situations by combining aspects of previous experiences. These models leverage compositional architectures which aim to learn specialized modules dedicated to…
We propose a method for autonomously learning an object-centric representation of a continuous and high-dimensional environment that is suitable for planning. Such representations can immediately be transferred between tasks that share the same types of objects, resulting in agents that require fewe…
We leverage logical composition in reinforcement learning to create a framework that enables an agent to autonomously determine whether a new task can be immediately solved using its existing abilities, or whether a task-specific skill should be learned. In the latter case, the proposed algorithm al…
The ability to compose learned skills to solve new tasks is an important property for lifelong-learning agents. In this work we formalise the logical composition of tasks as a Boolean algebra. This allows us to formulate new tasks in terms of the negation, disjunction and conjunction of a set of bas…
We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments. We show that these abstract representations can be learned in a task-independent egocentric space specific to the agent that, when grounded with problem-specif…
An important property for lifelong-learning agents is the ability to combine existing skills to solve new unseen tasks. In general, however, it is unclear how to compose existing skills in a principled manner. Under the assumption of deterministic dynamics, we prove that optimal value function compo…
Online learning of a robot's inverse dynamics model for trajectory tracking necessitates an interaction between the robot and its environment to collect training data. This is challenging for physical robots in the real world, especially for humanoids and manipulators due to their large and high dim…
Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, learning an appropriate hierarchical decomposition of a domain into subtasks remains a substantial challenge. We present a novel algorithm for subtask discovery, based on…
Trajectory planning and replanning in complex environments often reuses very little information from the previous solutions. This is particularly evident when the motion is repeated multiple times with only a limited amount of variation between each run. To address this issue, we propose the DRM-con…
Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a propositional object-oriented framework that has provably efficient learning bounds with respect to sample complexity. However, this framework has limitations in te…
Hierarchical architectures are critical to the scalability of reinforcement learning methods. Most current hierarchical frameworks execute actions serially, with macro-actions comprising sequences of primitive actions. We propose a novel alternative to these control hierarchies based on concurrent e…
This work proposes a framework that enables arbitrary robots with unknown kinematics models to imitate human demonstrations to acquire a skill, and reproduce it in real-time. The diversity of robots active in non-laboratory environments is growing constantly, and to this end we present an approach f…
We present a method for segmenting a set of unstructured demonstration trajectories to discover reusable skills using inverse reinforcement learning (IRL). Each skill is characterised by a latent reward function which the demonstrator is assumed to be optimizing. The skill boundaries and the number…