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

Recently, multiple approaches for creating agents for playing various complexreal-time computer games such as StarCraft II or Dota 2 were proposed, however,they either embed a significant amount of expert knowledge into the agent oruse a prohibitively large for most researchers amount of computationalresources. We propose a neural network architecture for playing the fulltwo-player match of StarCraft II trained with general-purpose supervised andreinforcement learning, that can be trained on a single consumer-grade PC witha single GPU. We also show that our implementation achieves a non-trivialperformance when compared to the in-game scripted bots. We make no simplifyingassumptions about the game except for playing on a single chosen map, and weuse very little expert knowledge. In principle, our approach can be applied toany RTS game with small modifications. While our results are far behind thestate-of-the-art large-scale approaches in terms of the final performance, webelieve our work can serve as a solid baseline for other small-scaleexperiments.

Applying supervised and reinforcement learning methods to create neural-network-based agents for playing StarCraft II