An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models

arXiv:2404.15518v1 Announce Type: new
Abstract: In traditional statistical learning, data points are usually assumed to be independently and identically distributed (i.i.d.) following an unknown probability distribution. This paper presents a contrasting viewpoint, perceiving data points as interconnected and employing a Markov reward process (MRP) for data modeling. We reformulate the typical supervised learning as an on-policy policy evaluation problem within reinforcement learning (RL), introducing a generalized temporal difference (TD) learning algorithm as a resolution. Theoretically, our analysis draws connections between …

abstract arxiv cs.ai cs.lg data data modeling difference distributed distribution generalized markov modeling paper probability process statistical supervised learning temporal type