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

We study multi-agent reinforcement learning (MARL) with centralized trainingand decentralized execution. During the training, new agents may join, andexisting agents may unexpectedly leave the training. In such situations, astandard deep MARL model must be trained again from scratch, which is verytime-consuming. To tackle this problem, we propose a special networkarchitecture with a few-shot learning algorithm that allows the number ofagents to vary during centralized training. In particular, when a new agentjoins the centralized training, our few-shot learning algorithm trains itspolicy network and value network using a small number of samples; when an agentleaves the training, the training process of the remaining agents is notaffected. Our experiments show that using the proposed network architecture andalgorithm, model adaptation when new agents join can be 100+ times faster thanthe baseline. Our work is applicable to any setting, including cooperative,competitive, and mixed.

Transferable Multi-Agent Reinforcement Learning with Dynamic Participating Agents