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/

Zendy Plus

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

Zendy Tools

Zendy Open

Deep reinforcement learning (DRL) is a booming area of artificialintelligence. Many practical applications of DRL naturally involve more thanone collaborative learners, making it important to study DRL in a multi-agentcontext. Previous research showed that effective learning in complexmulti-agent systems demands for highly coordinated environment explorationamong all the participating agents. Many researchers attempted to cope withthis challenge through learning centralized value functions. However, thecommon strategy for every agent to learn their local policies directly oftenfail to nurture strong inter-agent collaboration and can be sample inefficientwhenever agents alter their communication channels. To address these issues, wepropose a new framework known as centralized training and exploration withdecentralized execution via policy distillation. Guided by this framework andthe maximum-entropy learning technique, we will first train agents' policieswith shared global component to foster coordinated and effective learning.Locally executable policies will be derived subsequently from the trainedglobal policies via policy distillation. Experiments show that our newframework and algorithm can achieve significantly better performance and highersample efficiency than a cutting-edge baseline on several multi-agent DRLbenchmarks.

A New Framework for Multi-Agent Reinforcement Learning -- Centralized Training and Exploration with Decentralized Execution via Policy Distillation