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

The field of safe multi-agent reinforcement learning, despite its potentialapplications in various domains such as drone delivery and vehicle automation,remains relatively unexplored. Training agents to learn optimal policies thatmaximize rewards while considering specific constraints can be challenging,particularly in scenarios where having a central controller to coordinate theagents during the training process is not feasible. In this paper, we addressthe problem of multi-agent policy optimization in a decentralized setting,where agents communicate with their neighbors to maximize the sum of theircumulative rewards while also satisfying each agent's safety constraints. Weconsider both peak and average constraints. In this scenario, there is nocentral controller coordinating the agents and both the rewards and constraintsare only known to each agent locally/privately. We formulate the problem as adecentralized constrained multi-agent Markov Decision Problem and propose amomentum-based decentralized policy gradient method, DePAint, to solve it. Tothe best of our knowledge, this is the first privacy-preserving fullydecentralized multi-agent reinforcement learning algorithm that considers bothpeak and average constraints. We also provide theoretical analysis andempirical evaluation of our algorithm in various scenarios and compare itsperformance to centralized algorithms that consider similar constraints.

DePAint: A Decentralized Safe Multi-Agent Reinforcement Learning Algorithm considering Peak and Average Constraints