English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep Reinforcement Learning has been shown to be very successful in complexgames, e.g. Atari or Go. These games have clearly defined rules, and henceallow simulation. In many practical applications, however, interactions withthe environment are costly and a good simulator of the environment is notavailable. Further, as environments differ by application, the optimalinductive bias (architecture, hyperparameters, etc.) of a reinforcement agentdepends on the application. In this work, we propose a multi-arm banditframework that selects from a set of different reinforcement learning agents tochoose the one with the best inductive bias. To alleviate the problem of sparserewards, the reinforcement learning agents are augmented with surrogaterewards. This helps the bandit framework to select the best agents early, sincethese rewards are smoother and less sparse than the environment reward. Thebandit has the double objective of maximizing the reward while the agents arelearning and selecting the best agent after a finite number of learning steps.Our experimental results on standard environments show that the proposedframework is able to consistently select the optimal agent after a finitenumber of steps, while collecting more cumulative reward compared to selectinga sub-optimal architecture or uniformly alternating between different agents.

A Bandit Framework for Optimal Selection of Reinforcement Learning Agents