197 citations · 203 across the 8 of their papers we have counts for
9 papers
Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
Clément Bonnet, Daniel Luo, Donal Byrne +21
Open-source reinforcement learning (RL) environments have played a crucial role in driving progress in the development of AI algorithms. In modern RL research, there is a need for…
DITTO: Offline Imitation Learning with World Models
Branton DeMoss, Paul Duckworth, Jakob Foerster +2
For imitation learning algorithms to scale to real-world challenges, they must handle high-dimensional observations, offline learning, and policy-induced covariate-shift. We propos…
Invariant Risk Minimisation for Cross-Organism Inference: Substituting Mouse Data for Human Data in Human Risk Factor Discovery
Odhran O'Donoghue, Paul Duckworth, Giuseppe Ughi +10
Human medical data can be challenging to obtain due to data privacy concerns, difficulties conducting certain types of experiments, or prohibitive associated costs. In many setting…
Planning for Risk-Aversion and Expected Value in MDPs
Marc Rigter, Paul Duckworth, Bruno Lacerda +1
Planning in Markov decision processes (MDPs) typically optimises the expected cost. However, optimising the expectation does not consider the risk that for any given run of the MDP…
Risk-Aware Motion Planning in Partially Known Environments
Fernando S. Barbosa, Bruno Lacerda, Paul Duckworth +2
Recent trends envisage robots being deployed in areas deemed dangerous to humans, such as buildings with gas and radiation leaks. In such situations, the model of the underlying ha…
On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inference
Mohamed Baioumy, Bruno Lacerda, Paul Duckworth +1
Previous work on planning as active inference addresses finite horizon problems and solutions valid for online planning. We propose solving the general Stochastic Shortest-Path Mar…
Active Inference for Integrated State-Estimation, Control, and Learning
Mohamed Baioumy, Paul Duckworth, Bruno Lacerda +1
This work presents an approach for control, state-estimation and learning model (hyper)parameters for robotic manipulators. It is based on the active inference framework, prominent…
Towards better healthcare: What could and should be automated?
Wolfgang Frühwirt, Paul Duckworth
While artificial intelligence (AI) and other automation technologies might lead to enormous progress in healthcare, they may also have undesired consequences for people working in…
The STRANDS Project: Long-Term Autonomy in Everyday Environments
Nick Hawes, Chris Burbridge, Ferdian Jovan +30
Thanks to the efforts of the robotics and autonomous systems community, robots are becoming ever more capable. There is also an increasing demand from end-users for autonomous serv…