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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We study the problem of learning exploration-exploitation strategies thateffectively adapt to dynamic environments, where the task may change over time.While RNN-based policies could in principle represent such strategies, inpractice their training time is prohibitive and the learning process oftenconverges to poor solutions. In this paper, we consider the case where theagent has access to a description of the task (e.g., a task id or taskparameters) at training time, but not at test time. We propose a novelalgorithm that regularizes the training of an RNN-based policy using informedpolicies trained to maximize the reward in each task. This dramatically reducesthe sample complexity of training RNN-based policies, without losing theirrepresentational power. As a result, our method learns exploration strategiesthat efficiently balance between gathering information about the unknown andchanging task and maximizing the reward over time. We test the performance ofour algorithm in a variety of environments where tasks may vary within eachepisode.

Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization