Multi-Agent Actor-Critic Multitask Reinforcement Learning based on GTD(1) with Consensus-Reference-Cited by-同舟云学术

Multi-Agent Actor-Critic Multitask Reinforcement Learning based on GTD(1) with Consensus

Published:2022-12-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE 61st Conference on Decision and Control (CDC)
language:
Short-container-title:

Author:

Stankovic Milos S.¹,Beko Marko²,Ilic Nemanja³,Stankovic Srdjan S.⁴

Affiliation:

1. University Singidunum,Belgrade,Serbia

2. Universidade de Lisboa,Instituto de Telecomunicações, Instituto Superior Técnico,Lisbon,Portugal

3. College of Applied Technical Sciences,Kruševac,Serbia

4. University of Belgrade,School of Electrical Engineering,Serbia

Funder

Science Fund of the Republic of Serbia

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9992315/9992317/09992951.pdf?arnumber=9992951

Reference36 articles.

1. A decentralized policy gradient approach to multi-task reinforcement learning;zeng;Proceedings of Conferences on Uncertainty in Artificial Intelligence,2021

2. Stochastic Approximation and Recursive Estimation

3. Primal-Dual Algorithm for Distributed Reinforcement Learning: Distributed GTD

4. A multi-agent off-policy actor-critic algorithm for distributed reinforcement learning;suttle,2019

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Distributed Multi-Agent Gradient Based Q-Learning with Linear Function Approximation;2024 European Control Conference (ECC);2024-06-25

2. Distributed entropy-regularized multi-agent reinforcement learning with policy consensus;Automatica;2024-06

3. Multi-agent off-policy actor-critic algorithm for distributed multi-task reinforcement learning;European Journal of Control;2023-11