Optimizing average reward using discounted rewards

DOI10.1007/3-540-44581-1_40MaRDI QIDQ3148831zbMATH OpenFDO

Authors Sham M. Kakade

Publication date 22 September 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2111/21110605

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Recommendations

• Approximate gradient methods in policy-space optimization of Markov reward processes
• On average versus discounted reward temporal-difference learning
• LC-learning: Phased method for average reward reinforcement learning -- analysis of optimal criteria
• scientific article; zbMATH DE number 1753152

Cited in

(6)

• An expected average reward criterion
• Discounted reward TSP
• LC-learning: Phased method for average reward reinforcement learning -- analysis of optimal criteria
• Queueing network controls via deep reinforcement learning
• Smoothing policies and safe policy gradients
• MAdam: MLMC Adam under Markovian noise with application to average-reward policy optimization

This page was built for publication: Optimizing average reward using discounted rewards

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3148831)