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

Although deep reinforcement learning has led to breakthroughs in manydifficult domains, these successes have required an ever-increasing number ofsamples, affording only a shrinking segment of the AI community access to theirdevelopment. Resolution of these limitations requires new, sample-efficientmethods. To facilitate research in this direction, we propose this seconditeration of the MineRL Competition. The primary goal of the competition is tofoster the development of algorithms which can efficiently leverage humandemonstrations to drastically reduce the number of samples needed to solvecomplex, hierarchical, and sparse environments. To that end, participantscompete under a limited environment sample-complexity budget to develop systemswhich solve the MineRL ObtainDiamond task in Minecraft, a sequential decisionmaking environment requiring long-term planning, hierarchical control, andefficient exploration methods. The competition is structured into two rounds inwhich competitors are provided several paired versions of the dataset andenvironment with different game textures and shaders. At the end of each round,competitors submit containerized versions of their learning algorithms to theAIcrowd platform where they are trained from scratch on a hold-outdataset-environment pair for a total of 4-days on a pre-specified hardwareplatform. In this follow-up iteration to the NeurIPS 2019 MineRL Competition,we implement new features to expand the scale and reach of the competition. Inresponse to the feedback of the previous participants, we introduce a secondminor track focusing on solutions without access to environment interactions ofany kind except during test-time. Further we aim to prompt domain agnosticsubmissions by implementing several novel competition mechanics includingaction-space randomization and desemantization of observations and actions.

The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors