Distributed Actor-Critic Learning Using Emphatic Weightings-Reference-Cited by-同舟云学术

Distributed Actor-Critic Learning Using Emphatic Weightings

Published:2022-05-17 Issue: Volume: Page:
ISSN:
Container-title:2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)
language:
Short-container-title:

Author:

Stankovic Milos S.¹,Beko Marko²,Stankovic Srdjan S.³

Affiliation:

1. University Singidunum,Belgrade,Serbia

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

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

Funder

Fundaçõo para a Ciência e a Tecnologia

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9803856/9803880/09804022.pdf?arnumber=9804022

Reference34 articles.

1. Asymptotic Properties of Distributed and Communicating Stochastic Approximation Algorithms

2. Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize;yu;Journal of Machine Learning Research,2016

3. On convergence of emphatic temporal-difference learning;yu;Proceedings of The 28th Conference on Learning Theory,0

4. On convergence of some gradient-based temporal-differences algorithms for off-policy learning;yu;ArXiv,2017

Cited by 2 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. Multi-agent off-policy actor-critic algorithm for distributed multi-task reinforcement learning;European Journal of Control;2023-11

2. Multi-Agent Actor-Critic Multitask Reinforcement Learning based on GTD(1) with Consensus;2022 IEEE 61st Conference on Decision and Control (CDC);2022-12-06