Lecture Notes on Partially Known MDPs
arXiv:2112.02976v2
Originality Synthesis-oriented
AI Analysis
This is an incremental tutorial or lecture notes on a foundational topic in reinforcement learning, with no new contributions claimed.
The paper addresses the problem of finding optimal policies for Markov decision processes (MDPs) that are not fully known, transitioning from offline to online settings towards reinforcement learning, but no specific results or numbers are provided.
In these notes we will tackle the problem of finding optimal policies for Markov decision processes (MDPs) which are not fully known to us. Our intention is to slowly transition from an offline setting to an online (learning) setting. Namely, we are moving towards reinforcement learning.