# Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processes

## TL;DR

This paper presents an improved HiP-MDP framework that models joint uncertainty with scalable Bayesian Neural Networks, enabling efficient transfer learning across complex, high-dimensional tasks.

## Contribution

It introduces a new HiP-MDP formulation with joint uncertainty modeling and replaces Gaussian Processes with Bayesian Neural Networks for scalability.

## Key findings

- Enhanced modeling of joint uncertainty in HiP-MDPs
- Scalable inference with Bayesian Neural Networks
- Broader applicability to complex, high-dimensional tasks

## Abstract

We introduce a new formulation of the Hidden Parameter Markov Decision Process (HiP-MDP), a framework for modeling families of related tasks using low-dimensional latent embeddings. Our new framework correctly models the joint uncertainty in the latent parameters and the state space. We also replace the original Gaussian Process-based model with a Bayesian Neural Network, enabling more scalable inference. Thus, we expand the scope of the HiP-MDP to applications with higher dimensions and more complex dynamics.