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

Most existing deep reinforcement learning (DRL) frameworks consider eitherdiscrete action space or continuous action space solely. Motivated byapplications in computer games, we consider the scenario withdiscrete-continuous hybrid action space. To handle hybrid action space,previous works either approximate the hybrid space by discretization, or relaxit into a continuous set. In this paper, we propose a parametrized deepQ-network (P- DQN) framework for the hybrid action space without approximationor relaxation. Our algorithm combines the spirits of both DQN (dealing withdiscrete action space) and DDPG (dealing with continuous action space) byseamlessly integrating them. Empirical results on a simulation example, scoringa goal in simulated RoboCup soccer and the solo mode in game King of Glory(KOG) validate the efficiency and effectiveness of our method.

Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space