By Topic

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

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Kar, S. ; Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA ; Moura, J.M.F. ; Poor, H.V.

The paper develops Q D-learning, a distributed version of reinforcement Q -learning, for multi-agent Markov decision processes (MDPs); the agents have no prior information on the global state transition and on the local agent cost statistics. The network agents minimize a network-averaged infinite horizon discounted cost, by local processing and by collaborating through mutual information exchange over a sparse (possibly stochastic) communication network. The agents respond differently (depending on their instantaneous one-stage random costs) to a global controlled state and the control actions of a remote controller. When each agent is aware only of its local online cost data and the inter-agent communication network is weakly connected, we prove that Q D-learning, a consensus + innovations algorithm with mixed time-scale stochastic dynamics, converges asymptotically almost surely to the desired value function and to the optimal stationary control policy at each network agent.

Published in:

Signal Processing, IEEE Transactions on  (Volume:61 ,  Issue: 7 )