${{\cal Q} {\cal D}}$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through ${\rm Consensus} + {\rm Innovations}$

DOI10.1109/TSP.2013.2241057zbMath1393.94293arXiv1205.0047OpenAlexW1918371733MaRDI QIDQ4578509

José M. F. Moura, Soummya Kar, H. Vincent Poor

Publication date: 22 August 2018

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1205.0047

Mathematics Subject Classification ID

Applications of stochastic analysis (to PDEs, etc.) (60H30) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Stochastic approximation (62L20) Markov and semi-Markov decision processes (90C40)

Related Items (8)

Sequencing of multi-robot behaviors using reinforcement learning ⋮ Scalable Reinforcement Learning for Multiagent Networked Systems ⋮ A Discrete-Time Switching System Analysis of Q-Learning ⋮ Distributed consensus-based multi-agent temporal-difference learning ⋮ Distributed web hacking by adaptive consensus-based reinforcement learning ⋮ Fully asynchronous policy evaluation in distributed reinforcement learning over networks ⋮ Finite-Time Performance of Distributed Temporal-Difference Learning with Linear Function Approximation ⋮ Multi-agent reinforcement learning: a selective overview of theories and algorithms

This page was built for publication: ${{\cal Q} {\cal D}}$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through ${\rm Consensus} + {\rm Innovations}$