Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
average reward
Description:
The long-run expected reward per unit time or decision step in a sequential decision problem, such as a Markov decision process.
Primary topic:
Reinforcement Learning in Robotics (38%)
Related topics:
Reinforcement Learning in Robotics (38%),
Adaptive Dynamic Programming Control (15%),
Advanced Bandit Algorithms Research (8%)
OpenAlex ID:
keywords/average-reward
Chapter 8 Markov decision processes
1990
·
Martin L. Puterman
·
Handbooks in operations research and management science
·
967
Infinite-Horizon Policy-Gradient Estimation
2001
·
J. Baxter
, P. L. Bartlett
·
Journal of Artificial Intelligence Research
·
852
PDF
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
2004
·
Evan Greensmith
, Peter L. Bartlett
, et al.
·
Machine Learning
·
644
Formal verification of probabilistic systems
1997
·
Zohar Manna
, Luca de Alfaro
·
475
Speed/Accuracy Trade-Off between the Habitual and the Goal-Directed Processes
2011
·
Mehdi Keramati
, Amir Dezfouli
, et al.
·
PLoS Computational Biology
·
429
PDF
Indexability of Restless Bandit Problems and Optimality of Whittle Index for Dynamic Multichannel Access
2010
·
Keqin Liu
, Qing Zhao
·
IEEE Transactions on Information Theory
·
411
Learning the opportunity cost of time in a patch-foraging task
2015
·
Sara M. Constantino
, Nathaniel D. Daw
·
Cognitive Affective & Behavioral Neuroscience
·
292
PDF
Experiments with Infinite-Horizon, Policy-Gradient Estimation
2001
·
J. Baxter
, P. L. Bartlett
, et al.
·
Journal of Artificial Intelligence Research
·
159
PDF
Bias in Natural Actor-Critic Algorithms
2014
·
Philip S. Thomas
·
149
Optimistic Posterior Sampling for Reinforcement Learning: Worst-Case Regret Bounds
2022
·
Shipra Agrawal
, Randy Jia
·
Mathematics of Operations Research
·
139
PDF
New Criteria and a New Algorithm for Learning in Multi-Agent Systems
2004
·
Rob Powers
, Yoav Shoham
·
neural information processing systems
·
129
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes
2020
·
Chen-Yu Wei
, Mehdi Jafarnia
, et al.
·
International Conference on Machine Learning
·
127
Meta-Q-Learning
2019
·
Fakoor, Rasool
, Chaudhari, Pratik
, et al.
·
arXiv (Cornell University)
·
122
PDF
Batch policy learning in average reward Markov decision processes
2022
·
Peng Liao
, Zhengling Qi
, et al.
·
The Annals of Statistics
·
118
PDF
Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards
2020
·
Siddique, Umer
, Weng, Paul
, et al.
·
arXiv (Cornell University)
·
111
PDF
Learned Helplessness and Learned Prevalence: Exploring the Causal Relations Among Perceived Controllability, Reward Prevalence, and Exploration
2014
·
Kinneret Teodorescu
, Ido Erev
·
Psychological Science
·
111
Direct gradient-based reinforcement learning
2002
·
J. Baxter
, P.L. Bartlett
·
IEEE International Symposium on Circuits and Systems proceedings
·
111
Constrained Undiscounted Stochastic Dynamic Programming
1984
·
A. Hordijk
, L. C. M. Kallenberg
·
Mathematics of Operations Research
·
111
A Reinforcement Learning Algorithm Based on Policy Iteration for Average Reward: Empirical Results with Yield Management and Convergence Analysis
2004
·
Abhijit Gosavi
·
Machine Learning
·
105
PDF
Constrained Semi-Markov decision processes with average rewards
1994
·
Eugene A. Feinberg
·
Mathematical Methods of Operations Research
·
101
Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward
2020
·
Qu, Guannan
, Lin, Yiheng
, et al.
·
neural information processing systems
·
100
Whittle index based Q-learning for restless bandits with average reward
2022
·
Konstantin E. Avrachenkov
, Vivek S. Borkar
·
Automatica
·
91
PDF
Reinforcement Learning in POMDP's via Direct Gradient Ascent
2025
·
Baxter, Jonathan
, Bartlett, Peter L.
·
arXiv (Cornell University)
·
90
PDF
On Finite-Time Convergence of Actor-Critic Algorithm
2021
·
Shuang Qiu
, Zhuoran Yang
, et al.
·
IEEE Journal on Selected Areas in Information Theory
·
87
Optimal control of random walks, birth and death processes, and queues
1981
·
Richard Serfozo
·
Advances in Applied Probability
·
85
Show more works
View as search
Works count:
395
Citation count:
9,724
Year
Topic
Type