We consider robot learning in the context of shared autonomy, where cont...
There has been a recent surge of interest in developing generally-capabl...
Many sequential decision-making problems that are currently automated, s...
Offline reinforcement learning (RL) is suitable for safety-critical doma...
Offline reinforcement learning (RL) aims to find near-optimal policies f...
We consider a novel queuing problem where the decision-maker must choose...
Planning in Markov decision processes (MDPs) typically optimises the exp...
In this work, we address risk-averse Bayesadaptive reinforcement learnin...
The parameters for a Markov Decision Process (MDP) often cannot be speci...