Poster

Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes

Taylor Killian ⋅ Samuel Daulton ⋅ Finale Doshi-Velez ⋅ George Konidaris

Keywords: Multitask and Transfer Learning Reinforcement Learning and Planning Latent Variable Models Reinforcement Learning Model-Based RL Markov Decision Processes

2017 Poster

[ Code] [ Paper]

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.

Chat is not available.