Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations

08/15/2013
by   Finale Doshi-Velez, et al.
0

Control applications often feature tasks with similar, but not identical, dynamics. We introduce the Hidden Parameter Markov Decision Process (HiP-MDP), a framework that parametrizes a family of related dynamical systems with a low-dimensional set of latent factors, and introduce a semiparametric regression approach for learning its structure from data. In the control setting, we show that a learned HiP-MDP rapidly identifies the dynamics of a new task instance, allowing an agent to flexibly adapt to task variations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/20/2017

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

We introduce a new formulation of the Hidden Parameter Markov Decision P...
research
12/01/2016

Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes

Due to physiological variation, patients diagnosed with the same conditi...
research
04/25/2017

Sufficient Markov Decision Processes with Alternating Deep Neural Networks

Advances in mobile computing technologies have made it possible to monit...
research
02/08/2020

Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trials

There is broad interest in creating RL agents that can solve many (relat...
research
10/27/2021

Play to Grade: Testing Coding Games as Classifying Markov Decision Process

Contemporary coding education often presents students with the task of d...
research
02/08/2015

Contextual Markov Decision Processes

We consider a planning problem where the dynamics and rewards of the env...
research
06/10/2022

Conformal Prediction Intervals for Markov Decision Process Trajectories

Before delegating a task to an autonomous system, a human operator may w...

Please sign up or login with your details

Forgot password? Click here to reset