Deep reinforcement learning: Difference between revisions

Revision as of 03:51, 17 November 2023

Revision as of 03:52, 17 November 2023

Line 14:

=== Deep reinforcement learning ===

In many practical decision-making problems, the states <math>s</math> of the MDP are high-dimensional (e.g., images from a camera or the raw sensor stream from a robot) and cannot be solved by traditional RL algorithms. Deep reinforcement learning algorithms incorporate deep learning to solve such MDPs, often representing the policy <math>\pi(a|s)</math> or other learned functions as a neural network and developing specialized algorithms that perform well in this setting <ref name="link.springer.com">{{cite book |last1=Li |first1=Shenbo Eben |title= Reinforcement Learning for Sequential Decision and Optimal Control |date=2023 |___location=Springer Verlag, Singapore |isbn=978-9-811-97783-1 |pages=1–460 |doi=10.1007/978-981-19-7784-8 |edition=First | url=https://link.springer.com/book/10.1007/978-981-19-7784-8}}</ref>.

== History ==