ME Taylor, P Stone - … 24th international conference on Machine learning, 2007 - dl.acm.org
… domains, where we informally define a domain to be a setting for a group of semantically similar tasks. Such cross-domain … options across continuous reinforcementlearningdomains. …
… a problem that may otherwise be too difficult to learn from scratch. In this article, we present a framework for curriculum learning (CL) in reinforcementlearning, and use it to survey and …
Y Li - arXiv preprint arXiv:1701.07274, 2017 - arxiv.org
We give an overview of recent exciting achievements of deep reinforcementlearning (RL). We discuss six core elements, six important mechanisms, and twelve applications. We start …
… of reinforcementlearning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning… world as a problem domain ever since the field …
… ReinforcementLearning Background This monograph focuses on transfer learning in reinforcementlearningdomains; some RL background is necessary. Our goal in this chapter is to …
We consider the problem of generalization in reinforcementlearning where visual aspects of the observations might differ, eg when there are different backgrounds or change in contrast…
… have proven effective at solving reinforcementlearning (RL) … , a standard RL benchmark domain based on robot soccer. In … Our results in this domain demonstrate that NEAT discovers …
… the past on simple domains like grid … reinforcementlearning algorithms with on-line algorithms based on their empirical performance in a complex, continuous, noisy, multiagent domain, …
… domain transfer. Also, while our work focused on discrete and deterministic environments, we believe that transfer learning … difficulty of applying reinforcementlearning methods directly …