55 citations · 60 across the 28 of their papers we have counts for
12 papers · 1 filter
Benchmarking World Models for Continual Learning on Compositional Tasks
Haoyu Zhou, Joe Watson, Anson Lei +1
A desirable property of a world model is the ability to learn continually across tasks, adapting to new environments without forgetting what the agent has already learnt. In partic…
Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
Christian Scherer, Joe Watson, Theo Gruner +3
Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for…
No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation
Bradley Stanley-Clamp, Anson Lei, Hannah M. Christensen +1
Climate emulation is an out-of-distribution (OOD) projection task. This is precisely the challenge where modern Machine Learning (ML) methods are most prone to failure. Consequentl…
XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies
Daniel Palenicek, Florian Vogt, Joe Watson +3
For reinforcement learning in the real world online exploration is expensive A common practice in robotic reinforcement learning is to incorporate additional data to improve sample…
Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention
Markus W. Baumgartner, Anson Lei, Joe Watson +1
Parametric system identification methods estimate the parameters of explicitly defined physical systems from data. Yet, they remain constrained by the need to provide an explicit f…
Intrinsically Interpretable Attention via Sparse Post-Training
Florent Draye, Anson Lei, Hsiao-Ru Pan +2
We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-…
XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning
Daniel Palenicek, Florian Vogt, Joe Watson +2
Sample efficiency is a central property of effective deep reinforcement learning algorithms. Recent work has improved this through added complexity, such as larger models, exotic n…
SPARTAN: A Sparse Transformer World Model Attending to What Matters
Anson Lei, Bernhard Schölkopf, Ingmar Posner
Capturing the interactions between entities in a structured way plays a central role in world models that flexibly adapt to changes in the environment. Recent works motivate the be…
Compete and Compose: Learning Independent Mechanisms for Modular World Models
Anson Lei, Frederik Nolte, Bernhard Schölkopf +1
We present COmpetitive Mechanisms for Efficient Transfer (COMET), a modular world model which leverages reusable, independent mechanisms across different environments. COMET is tra…
World Models via Policy-Guided Trajectory Diffusion
Marc Rigter, Jun Yamada, Ingmar Posner
World models are a powerful tool for developing intelligent agents. By predicting the outcome of a sequence of actions, world models enable policies to be optimised via on-policy r…
Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization
Haitz Saez de Ocariz Borde, Alvaro Arroyo, Ismael Morales +2
Recent research indicates that the performance of machine learning models can be improved by aligning the geometry of the latent space with the underlying data structure. Rather th…
Gromov-Hausdorff Distances for Comparing Product Manifolds of Model Spaces
Haitz Saez de Ocariz Borde, Alvaro Arroyo, Ismael Morales +2
Recent studies propose enhancing machine learning models by aligning the geometric characteristics of the latent space with the underlying data structure. Instead of relying solely…