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

Many tasks in practice require the collaboration of multiple agents throughreinforcement learning. In general, cooperative multiagent reinforcementlearning algorithms can be classified into two paradigms: Joint Action Learners(JALs) and Independent Learners (ILs). In many practical applications, agentsare unable to observe other agents' actions and rewards, making JALsinapplicable. In this work, we focus on independent learning paradigm in whicheach agent makes decisions based on its local observations only. However,learning is challenging in independent settings due to the local viewpoints ofall agents, which perceive the world as a non-stationary environment due to theconcurrently exploring teammates. In this paper, we propose a novel frameworkcalled Independent Generative Adversarial Self-Imitation Learning (IGASIL) toaddress the coordination problems in fully cooperative multiagent environments.To the best of our knowledge, we are the first to combine self-imitationlearning with generative adversarial imitation learning (GAIL) and apply it tocooperative multiagent systems. Besides, we put forward a Sub-CurriculumExperience Replay mechanism to pick out the past beneficial experiences as muchas possible and accelerate the self-imitation learning process. Evaluationsconducted in the testbed of StarCraft unit micromanagement and a commonlyadopted benchmark show that our IGASIL produces state-of-the-art results andeven outperforms JALs in terms of both convergence speed and final performance.

Independent Generative Adversarial Self-Imitation Learning in Cooperative Multiagent Systems