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

2048 is an engaging single-player, nondeterministic video puzzle game, which,thanks to the simple rules and hard-to-master gameplay, has gained massivepopularity in recent years. As 2048 can be conveniently embedded into thediscrete-state Markov decision processes framework, we treat it as a testbedfor evaluating existing and new methods in reinforcement learning. With the aimto develop a strong 2048 playing program, we employ temporal differencelearning with systematic n-tuple networks. We show that this basic method canbe significantly improved with temporal coherence learning, multi-stagefunction approximator with weight promotion, carousel shaping, and redundantencoding. In addition, we demonstrate how to take advantage of thecharacteristics of the n-tuple network, to improve the algorithmiceffectiveness of the learning process by i) delaying the (decayed) update andapplying lock-free optimistic parallelism to effortlessly make advantage ofmultiple CPU cores. This way, we were able to develop the best known 2048playing program to date, which confirms the effectiveness of the introducedmethods for discrete-state Markov decision problems.

Mastering 2048 with Delayed Temporal Coherence Learning, Multi-Stage Weight Promotion, Redundant Encoding and Carousel Shaping