Active Reinforcement Learning: Observing Rewards at a Cost

Active Reinforcement Learning: Observing Rewards at a Cost. Krueger, D; Leike, J; Evans, O; and Salvatier, J filmnips.com.
abstract bibtex

Abstract Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does not observe the reward unless it chooses to pay a query cost c> 0. The central question of ARL is how to quantify the long-term value of reward information. Even in multi-armed bandits, computing the value of this information is intractable and we have to rely on heuristics. We propose and evaluate several heuristic approaches for ARL in multi-.

@Article{Krueger,
author = {Krueger, D and Leike, J and Evans, O and Salvatier, J}, 
title = {Active Reinforcement Learning: Observing Rewards at a Cost}, 
journal = {filmnips.com}, 
volume = {}, 
number = {}, 
pages = {}, 
year = {}, 
abstract = {Abstract Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does not observe the reward unless it chooses to pay a query cost c\&gt; 0. The central question of ARL is how to quantify the long-term value of reward information. Even in multi-armed bandits, computing the value of this information is intractable and we have to rely on heuristics. We propose and evaluate several heuristic approaches for ARL in multi-.}, 
location = {}, 
keywords = {}}

Downloads: 0