Learning to Track Environment State

Marian Andrecki, Nicholas Kenelm Taylor

Research output: Contribution to conferencePaperpeer-review

35 Downloads (Pure)


Reinforcement learning (RL) based on artificial neural networks (ANN) has seen great successes in recent years. A notable recent breakthrough came from Volodymyr Mnih, where an artificial agent learnt to play games from raw pixels on a screen with scores produced by Atari game console simulation. The algorithm managed to surpass human performance on many classic 1980s games. However, RL has not yet achieved similar successes for real world tasks, such as controlling robotic manipulation. RL requires dozens of hours of gameplay in order to perform at human level. This training time is currently a significant obstacle outside simulation systems. It has been argued that pure RL is data inefficient because the reward signal - the only feedback used - is sparse and contains little information.
One approach to extract more information from
agent's experiences is to train to predict future observa-
tions. In this work, we investigate learning of stochas-
tic forward models of environments from raw sensory
observations. Such models could be then used for prob-
abilistic state estimation, future prediction, planning,
and ultimately, more ecient beheviour. The overar-
ching goal is data-ecient reinforcement learning.
Original languageEnglish
Number of pages1
Publication statusPublished - 4 Jun 2018
Event2018 EPSRC CDT Student Conference – Oxford, Bristol and Edinburgh - Bristol, United Kingdom
Duration: 4 Jun 20185 Jun 2018


Conference2018 EPSRC CDT Student Conference – Oxford, Bristol and Edinburgh
Country/TerritoryUnited Kingdom


Dive into the research topics of 'Learning to Track Environment State'. Together they form a unique fingerprint.

Cite this