DNA barcoding and nutritional profiling of some underutilized native indigenous plant species (NIPS) of Karnataka, India

Kumar, Roshni Mohan; Ramasetty, Bharathi Tumkur; Prakash, H. S.

doi:10.21203/rs.3.rs-2055009/v1

Cited by 1 publication

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also note that our DeCOM aims to solve CCMG, which involves constraints defined over long-term returns instead of each state (Wagener, Boots, and Cheng 2021;Sheebaelhamd et al 2021;Thomas, Luo, and Ma 2021). Furthermore, rather than analyzing linear or finite MDPs Efroni, Mannor, and Pirotta 2020;Liu et al 2021;Xu, Liang, and Lan 2021), DeCOM aims at high-dimensional real-world applications, which typically involve continuous controls and complex non-linear dynamics (Kumar et al 2020).…”

Section: Related Workmentioning

confidence: 99%

DeCOM: Decomposed Policy for Constrained Cooperative Multi-Agent Reinforcement Learning

Yang

Jin

Ding

et al. 2023

AAAI

View full text Add to dashboard Cite

In recent years, multi-agent reinforcement learning (MARL) has presented impressive performance in various applications. However, physical limitations, budget restrictions, and many other factors usually impose constraints on a multi-agent system (MAS), which cannot be handled by traditional MARL frameworks. Specifically, this paper focuses on constrained MASes where agents work cooperatively to maximize the expected team-average return under various constraints on expected team-average costs, and develops a constrained cooperative MARL framework, named DeCOM, for such MASes. In particular, DeCOM decomposes the policy of each agent into two modules, which empowers information sharing among agents to achieve better cooperation. In addition, with such modularization, the training algorithm of DeCOM separates the original constrained optimization into an unconstrained optimization on reward and a constraints satisfaction problem on costs. DeCOM then iteratively solves these problems in a computationally efficient manner, which makes DeCOM highly scalable. We also provide theoretical guarantees on the convergence of DeCOM's policy update algorithm. Finally, we conduct extensive experiments to show the effectiveness of DeCOM with various types of costs in both moderate-scale and large-scale (with 500 agents) environments that originate from real-world applications.

show abstract