In this section
@inproceedings{Sæmundsson:2018,
author = {Sæmundsson, S and Hofmann, K and Deisenroth, MP},
publisher = {Association for Uncertainty in Artificial Intelligence (AUAI)},
title = {Meta reinforcement learning with latent variable Gaussian processes},
url = {http://hdl.handle.net/10044/1/63752},
year = {2018}
}
TY - CPAPER
AB - Learning from small data sets is critical inmany practical applications where data col-lection is time consuming or expensive, e.g.,robotics, animal experiments or drug design.Meta learning is one way to increase the dataefficiency of learning algorithms by general-izing learned concepts from a set of trainingtasks to unseen, but related, tasks. Often, thisrelationship between tasks is hard coded or re-lies in some other way on human expertise.In this paper, we frame meta learning as a hi-erarchical latent variable model and infer therelationship between tasks automatically fromdata. We apply our framework in a model-based reinforcement learning setting and showthat our meta-learning model effectively gen-eralizes to novel tasks by identifying how newtasks relate to prior ones from minimal data.This results in up to a60%reduction in theaverage interaction time needed to solve taskscompared to strong baselines.
AU - Sæmundsson,S
AU - Hofmann,K
AU - Deisenroth,MP
PB - Association for Uncertainty in Artificial Intelligence (AUAI)
PY - 2018///
TI - Meta reinforcement learning with latent variable Gaussian processes
UR - http://hdl.handle.net/10044/1/63752
ER -
Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ
To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:
To reach the network manager, Diana O'Malley - including to join the network - please contact: