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

While most current research in Reinforcement Learning (RL) focuses onimproving the performance of the algorithms in controlled environments, the useof RL under constraints like those met in the video game industry is rarelystudied. Operating under such constraints, we propose Hybrid SAC, an extensionof the Soft Actor-Critic algorithm able to handle discrete, continuous andparameterized actions in a principled way. We show that Hybrid SAC cansuccessfully solve a highspeed driving task in one of our games, and iscompetitive with the state-of-the-art on parameterized actions benchmark tasks.We also explore the impact of using normalizing flows to enrich theexpressiveness of the policy at minimal computational cost, and identify apotential undesired effect of SAC when used with normalizing flows, that may beaddressed by optimizing a different objective.

Discrete and Continuous Action Representation for Practical RL in Video Games