… We present a distributional approach to theoretical analyses of reinforcement learning
algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and …

… This paper surveys the field of reinforcement learning from a … learning. Both the historical
basis of the field and a broad selection of current work are summarized. Reinforcement learning …

… RL-Glue lays a solid foundation for empirical analysis in reinforcement learning. RL-Glue is
very good and very useful software but is restricted to single objective reinforcement learning…

… paradigm which facilitates our empirical analysis of the difficulties in offline reinforcement …
detailed empirical analysis of the failure modes of passive (ie non-interactive, offline) learning, …

… the role that reinforcement learning can play in the optimization of treatment policies for
chronic illnesses. Before applying any off-the-shelf reinforcement learning methods in this setting…

… We begin our empirical analysis by comparing Sarsa and NEAT in the benchmark
versions of both the mountain car and keepaway tasks. The differences observed in these …

… Reproducibility of benchmarked deep reinforcement learning tasks for continuous control.
In: Proceedings of the ICML 2017 workshop on Reproducibility in Machine Learning (RML). …

… We begin by describing a simple observational study of a single reinforcement learning
agent. Only once we have mastered the art of observing our agents can we then begin to design …

… As we do not have the ability to generate more data through an exploration of novel treatment
strategies, we develop a policy using offline, batch reinforcement learning. In this setting, it …

… Reinforcement learning describes motivated behavior in terms of two … -analysis of functional
magnetic resonance imaging studies that had employed algorithmic reinforcement learning …