Planning under uncertainty is critical to robotics. The partially observable Markov decision
process (POMDP) is a mathematical framework for such planning problems. POMDPs are …

In this work, we address risk-averse Bayes-adaptive reinforcement learning. We pose the
problem of optimising the conditional value at risk (CVaR) of the total return in Bayes …

Rather than augmenting rewards with penalties for undesired behavior, Constrained
Partially Observable Markov Decision Processes (CPOMDPs) plan safely by imposing …

This paper introduces Voronoi Progressive Widening (VPW), a generalization of Voronoi
optimistic optimization (VOO) and action progressive widening to partially observable …

Partially observable Markov decision processes (POMDPs) provide a flexible representation
for real-world decision and control problems. However, POMDPs are notoriously difficult to …

Planning under uncertainty is critical to robotics. The Partially Observable Markov Decision
Process (POMDP) is a mathematical framework for such planning problems. It is powerful …

Autonomous exploration of unknown environments is fundamentally a problem of decision
making under uncertainty where the agent must account for uncertainty in sensor …

Optimal plans in Constrained Partially Observable Markov Decision Processes (CPOMDPs)
maximize reward objectives while satisfying hard cost constraints, generalizing safe …

Planning under partial obervability is essential for autonomous robots. A principled way to
address such planning problems is the Partially Observable Markov Decision Process …

The optimal design of a wind farm which maximizes energy production depends on the
spatially variable wind flow field. However, due to the complexity associated with modeling …