Discounted Reinforcement Learning Is Not an Optimization Problem

Abhishek Naik, Roshan Shariff, Niko Yasui, Hengshuai Yao, Richard S. Sutton

Type: Preprint

Publication Date: 2019-01-01

Citations: 24

DOI: https://doi.org/10.48550/arxiv.1910.02140

View Publication

Locations

arXiv (Cornell University) - View
DataCite API - View

Similar Works

Action	Title	Year	Authors
+	Examining average and discounted reward optimality criteria in reinforcement learning	2021	Vektor Dewanto Marcus Gallagher
+ PDF Chat	Reward Centering	2024	Abhishek Naik Yi Wan Manan Tomar Richard S. Sutton
+	Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks	2020	Yuqian Jiang Suda Bharadwaj Bo Wu Rishi Shah Ufuk Topcu Peter Stone
+ PDF Chat	Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks	2021	Yuqian Jiang Suda Bharadwaj Bo Wu Rishi Shah Ufuk Topcu Peter Stone
+	Delayed Geometric Discounts: An Alternative Criterion for Reinforcement Learning	2022	Firas Jarboui Ahmed Akakzia
+	Goodhart's Law in Reinforcement Learning	2023	Jacek Karwowski Oliver Hayman Xingjian Bai Klaus Kiendlhofer Charlie Griffin Joar Skalse
+ PDF Chat	Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning	2024	Shuyu Yin Wen Fei Peilin Liu Tao Luo
+	A General Perspective on Objectives of Reinforcement Learning	2023	Yang Long
+ PDF Chat	Examining Average and Discounted Reward Optimality Criteria in Reinforcement Learning	2022	Vektor Dewanto Marcus Gallagher
+ PDF Chat	Introduction to Reinforcement Learning	2024	Majid Ghasemi Dariush Ebrahimi
+	Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems	2020	Sergey Levine Aviral Kumar George Tucker Justin Fu
+ PDF Chat	Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach	2019	Silviu Pitis
+ PDF Chat	Effective Reward Specification in Deep Reinforcement Learning	2024	Julien Le Roy
+ PDF Chat	Reinforcement Learning: An Overview	2024	Kevin J. Murphy
+	Reward Tweaking: Maximizing the Total Reward While Planning for Short Horizons	2020	Chen Tessler Shie Mannor
+	Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach	2019	Silviu Pitis
+	A Definition of Continual Reinforcement Learning	2023	David Abel André Barreto Benjamin Van Roy Doina Precup Hado van Hasselt Satinder Singh
+	Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning	2019	Harm van Seijen Mehdi Fatemi Arash Tavakoli
+	Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning	2019	Harm van Seijen Mehdi Fatemi Arash Tavakoli
+	Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning	2019	Harm van Seijen Mehdi Fatemi Arash Tavakoli

Works That Cite This (12)

Action	Title	Year	Authors
+	Learning and Planning in Average-Reward Markov Decision Processes	2020	Yi Wan Abhishek Naik Richard S. Sutton
+	Planning with Expectation Models for Control.	2021	Katya Kudashkina Yi Wan Abhishek Naik Richard S. Sutton
+	A Scalable Federated Multi-agent Architecture for Networked Connected Communication Network	2021	Fenghe Hu Yansha Deng A.H. Aghvami
+ PDF Chat	Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks	2021	Yuqian Jiang Suda Bharadwaj Bo Wu Rishi Shah Ufuk Topcu Peter Stone
+	Scalable Multi-agent Reinforcement Learning Algorithm for Wireless Networks	2021	Fenghe Hu Yansha Deng A.H. Aghvami
+	Optimizing the Long-Term Average Reward for Continuing MDPs: A Technical Report	2021	Chao Xu Yiping Xie Xijun Wang Howard H. Yang Dusit Niyato Tony Q. S. Quek
+ PDF Chat	Data-driven control of micro-climate in buildings: An event-triggered reinforcement learning approach	2020	Ashkan Haji Hosseinloo Alexander Ryzhov Aldo Bischi H. Ouerdane Konstantin Turitsyn Munther A. Dahleh
+ PDF Chat	Reward Function Design for Crowd Simulation via Reinforcement Learning	2023	Ariel Kwiatkowski Vicky Kalogeiton Julien Pettré Marie‐Paule Cani
+	Model-Free Design of Stochastic LQR Controller from Reinforcement Learning and Primal-Dual Optimization Perspective	2021	Man Li Jiahu Qin Wei Xing Zheng Yaonan Wang Yu Kang
+ PDF Chat	Age-Based Scheduling for Mobile Edge Computing: A Deep Reinforcement Learning Approach	2024	Xingqiu He Chaoqun You Tony Q. S. Quek

Works Cited by This (5)

Action	Title	Year	Authors
+ PDF Chat	Learning Algorithms for Markov Decision Processes with Average Cost	2001	Jinane Abounadi Dimitri P. Bertsekas Vivek S. Borkar
+	Hyperbolic Discounting and Learning over Multiple Horizons	2019	William Fedus Carles Gelada Yoshua Bengio Marc G. Bellemare Hugo Larochelle
+	Issues concerning realizability of Blackwell optimal policies in reinforcement learning	2019	Nicholas J. Denis
+	Unifying task specification in reinforcement learning	2016	Martha White
+	Examples concerning Abel and Cesàro limits	2014	Christopher J. Bishop Eugene A. Feinberg Junyu Zhang