Much of reinforcement learning theory is built on top of oracles that are computationally hard
to implement. Specifically for learning near-optimal policies in Partially Observable Markov …

For reinforcement learning in environments in which an agent has access to a reliable state
signal, methods based on the Markov decision process (MDP) have had many successes. In …

A central problem in artificial intelligence is to choose actions to maximize reward in a
partially observable, uncertain environment. To do so, we must learn an accurate …

Particle filtering is a powerful approach to sequential state estimation and finds application
in many domains, including robot localization, object tracking, etc. To apply particle filtering …

This paper introduces the QMDP-net, a neural network architecture for planning under
partial observability. The QMDP-net combines the strengths of model-free learning and …

Online, sample-based planning algorithms for POMDPs have shown great promise in
scaling to problems with large state spaces, but they become intractable for large action and …

Abstract Solving Partially Observable Markov Decision Processes (POMDPs) is hard.
Learning optimal controllers for POMDPs when the model is unknown is harder. Online …

Robotic exploration tasks involve inherent uncertainty. They typically include navigating
through unknown terrain, searching for features that may or may not be present, and …

We seek to find the robust policy that maximizes the expected cumulative reward for the
worst case when a partially observable Markov decision process (POMDP) has uncertain …

Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning
domains that require balancing actions that increase an agent's knowledge and actions that …