English
Related papers

Related papers: A Tale of Sampling and Estimation in Discounted Re…

200 papers

We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components. Assuming the factorization is known, we propose two model-based…

Machine Learning · Computer Science 2020-06-25 Yi Tian , Jian Qian , Suvrit Sra

We establish that an optimistic variant of Q-learning applied to a fixed-horizon episodic Markov decision process with an aggregated state representation incurs regret $\tilde{\mathcal{O}}(\sqrt{H^5 M K} + \epsilon HK)$, where $H$ is the…

Machine Learning · Statistics 2020-02-20 Shi Dong , Benjamin Van Roy , Zhengyuan Zhou

Reinforcement learning (RL) agents have traditionally been tasked with maximizing the value function of a Markov decision process (MDP), either in continuous settings, with fixed discount factor $\gamma < 1$, or in episodic settings, with…

Machine Learning · Computer Science 2019-02-11 Silviu Pitis

In this paper we consider the problem of computing an $\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any…

Optimization and Control · Mathematics 2019-06-07 Aaron Sidford , Mengdi Wang , Xian Wu , Lin F. Yang , Yinyu Ye

This paper addresses the challenge of offline policy learning in reinforcement learning with continuous action spaces when unmeasured confounders are present. While most existing research focuses on policy evaluation within partially…

Machine Learning · Statistics 2025-05-02 Yuhan Li , Eugene Han , Yifan Hu , Wenzhuo Zhou , Zhengling Qi , Yifan Cui , Ruoqing Zhu

Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) -- the problem of evaluating a new policy using the historical data…

Machine Learning · Computer Science 2020-04-02 Tengyang Xie , Yifei Ma , Yu-Xiang Wang

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

Machine Learning · Computer Science 2021-05-06 Kurtland Chua , Qi Lei , Jason D. Lee

We tackle the problem of estimating risk measures of the infinite-horizon discounted cost within a Markov cost process. The risk measures we study include variance, Value-at-Risk (VaR), and Conditional Value-at-Risk (CVaR). First, we show…

Machine Learning · Computer Science 2024-04-12 Gugan Thoppe , L. A. Prashanth , Sanjay Bhat

This paper studies the problem of data collection for policy evaluation in Markov decision processes (MDPs). In policy evaluation, we are given a target policy and asked to estimate the expected cumulative reward it will obtain in an…

Machine Learning · Computer Science 2022-06-22 Subhojyoti Mukherjee , Josiah P. Hanna , Robert Nowak

This paper is concerned with the development of rigorous approximations to various expectations associated with Markov chains and processes having non-stationary transition probabilities. Such non-stationary models arise naturally in…

Probability · Mathematics 2018-05-07 Zeyu Zheng , Harsha Honnappa , Peter W. Glynn

Many popular policy gradient methods for reinforcement learning follow a biased approximation of the policy gradient known as the discounted approximation. While it has been shown that the discounted approximation of the policy gradient is…

Machine Learning · Computer Science 2023-01-10 Chris Nota

In an effort to better understand the different ways in which the discount factor affects the optimization process in reinforcement learning, we designed a set of experiments to study each effect in isolation. Our analysis reveals that the…

Machine Learning · Computer Science 2019-12-24 Harm van Seijen , Mehdi Fatemi , Arash Tavakoli

We consider the problem of estimating the missing mass, partition function or evidence and its probability distribution in the case that for each sample point in the discrete sample space its (unnormalized) probability mass is revealed.…

Statistics Theory · Mathematics 2026-03-16 Bastiaan J. Braams

We study safe reinforcement learning in finite-horizon linear mixture constrained Markov decision processes (CMDPs) with adversarial rewards under full-information feedback and an unknown transition kernel. We propose a primal-dual policy…

Machine Learning · Computer Science 2026-03-31 Kihyun Yu , Seoungbin Bae , Dabeen Lee

In this paper we provide faster algorithms for approximately solving discounted Markov Decision Processes in multiple parameter regimes. Given a discounted Markov Decision Process (DMDP) with $|S|$ states, $|A|$ actions, discount factor…

Data Structures and Algorithms · Computer Science 2020-12-24 Aaron Sidford , Mengdi Wang , Xian Wu , Yinyu Ye

This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns. Due…

Multiagent Systems · Computer Science 2022-12-06 Xiaoxiao Zhao , Jinlong Lei , Li Li , Jie Chen

This paper considers stochastic-constrained stochastic optimization where the stochastic constraint is to satisfy that the expectation of a random function is below a certain threshold. In particular, we study the setting where data samples…

Optimization and Control · Mathematics 2026-01-27 Yeongjong Kim , Dabeen Lee

We study the problem of infinite-horizon average-reward reinforcement learning with linear Markov decision processes (MDPs). The associated Bellman operator of the problem not being a contraction makes the algorithm design challenging.…

Machine Learning · Statistics 2025-03-12 Kihyuk Hong , Woojin Chae , Yufan Zhang , Dabeen Lee , Ambuj Tewari

This article presents a short and concise description of stochastic approximation algorithms in reinforcement learning of Markov decision processes. The algorithms can also be used as a suboptimal method for partially observed Markov…

Optimization and Control · Mathematics 2015-12-25 Vikram Krishnamurthy

In reinforcement learning, the discount factor $\gamma$ controls the agent's effective planning horizon. Traditionally, this parameter was considered part of the MDP; however, as deep reinforcement learning algorithms tend to become…

Machine Learning · Computer Science 2020-06-24 Chen Tessler , Shie Mannor
‹ Prev 1 3 4 5 6 7 10 Next ›