This thesis is a detailed investigation into the following question: how much data must an
agent collect in order to perform" reinforcement learning" successfully? This question is …

Training a deep neural network to maximize a target objective has become the standard
recipe for successful machine learning over the last decade. These networks can be …

With contributions from prominent scientists, this volume presents a scientific understanding
of humans with a view towards developing better-engineered systems and machines for …

The partially observable Markov decision process (POMDP) provides a principled general
framework for robot planning under uncertainty. Leveraging the idea of Monte Carlo …

Many real-world tasks require multiple decision makers (agents) to coordinate their actions
in order to achieve common long-term goals. Examples include: manufacturing systems …

This thesis considers three complications that arise from applying reinforcement learning to
a real-world application. In the process of using reinforcement learning to build an adaptive …

Partially observable Markov decision processes are interesting because of their ability to
model most conceivable real-world learning problems, for example, robot navigation, driving …

Artificial neural networks have been successfully incorporated into the variational Monte
Carlo method (VMC) to study quantum many-body systems. However, there have been few …

Searching the space of policies directly for the optimal policy has been one popular method
for solving partially observable reinforcement learning problems. Typically, with each …

This article proposes a field application of a Reinforcement Learning (RL) control system for
solving the action selection problem of an autonomous robot in a cable tracking task. The …