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

This paper describes an AI agent that plays the popular first-person-shooter(FPS) video game `Counter-Strike; Global Offensive' (CSGO) from pixel input.The agent, a deep neural network, matches the performance of the mediumdifficulty built-in AI on the deathmatch game mode, whilst adopting a humanlikeplay style. Unlike much prior work in games, no API is available for CSGO, soalgorithms must train and run in real-time. This limits the quantity ofon-policy data that can be generated, precluding many reinforcement learningalgorithms. Our solution uses behavioural cloning - training on a large noisydataset scraped from human play on online servers (4 million frames, comparablein size to ImageNet), and a smaller dataset of high-quality expertdemonstrations. This scale is an order of magnitude larger than prior work onimitation learning in FPS games.

Counter-Strike Deathmatch with Large-Scale Behavioural Cloning