English
Related papers

Related papers: Variance-Reduced Cascade Q-learning: Algorithms an…

200 papers

We introduce and analyze a form of variance-reduced $Q$-learning. For $\gamma$-discounted MDPs with finite state space $\mathcal{X}$ and action space $\mathcal{U}$, we prove that it yields an $\epsilon$-accurate estimate of the optimal…

Machine Learning · Computer Science 2019-08-09 Martin J. Wainwright

We consider model-free reinforcement learning for infinite-horizon discounted Markov Decision Processes (MDPs) with a continuous state space and unknown transition kernel, when only a single sample path under an arbitrary policy of the…

Machine Learning · Computer Science 2018-10-24 Devavrat Shah , Qiaomin Xie

We study a Q learning algorithm for continuous time stochastic control problems. The proposed algorithm uses the sampled state process by discretizing the state and control action spaces under piece-wise constant control processes. We show…

Optimization and Control · Mathematics 2023-03-10 Erhan Bayraktar , Ali Devran Kara

Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP), based on a single trajectory of Markovian samples induced by a behavior policy. Focusing on a $\gamma$-discounted…

Machine Learning · Computer Science 2022-09-13 Gen Li , Yuting Wei , Yuejie Chi , Yuantao Gu , Yuxin Chen

In an episodic Markov Decision Process (MDP) problem, an online algorithm chooses from a set of actions in a sequence of $H$ trials, where $H$ is the episode length, in order to maximize the total payoff of the chosen actions. Q-learning,…

Machine Learning · Computer Science 2019-07-11 Xu Zhu

Various algorithms in reinforcement learning exhibit dramatic variability in their convergence rates and ultimate accuracy as a function of the problem structure. Such instance-specific behavior is not captured by existing global minimax…

Machine Learning · Statistics 2021-06-29 Koulik Khamaru , Eric Xia , Martin J. Wainwright , Michael I. Jordan

The curse of dimensionality is a widely known issue in reinforcement learning (RL). In the tabular setting where the state space $\mathcal{S}$ and the action space $\mathcal{A}$ are both finite, to obtain a nearly optimal policy with…

Machine Learning · Computer Science 2022-10-28 Bingyan Wang , Yuling Yan , Jianqing Fan

Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which the data is collected can differ from that of the environment…

Machine Learning · Computer Science 2024-09-05 Shengbo Wang , Nian Si , Jose Blanchet , Zhengyuan Zhou

In Markov decision processes (MDPs), quantile risk measures such as Value-at-Risk are a standard metric for modeling RL agents' preferences for certain outcomes. This paper proposes a new Q-learning algorithm for quantile optimization in…

Machine Learning · Computer Science 2024-11-01 Jia Lin Hau , Erick Delage , Esther Derman , Mohammad Ghavamzadeh , Marek Petrik

Analyzing the Markov decision process (MDP) with continuous state spaces is generally challenging. A recent interesting work \cite{shah2018q} solves MDP with bounded continuous state space by a nearest neighbor $Q$ learning approach, which…

Machine Learning · Computer Science 2024-06-18 Puning Zhao , Lifeng Lai

Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all…

Machine Learning · Statistics 2025-03-18 Gen Li , Changxiao Cai , Yuxin Chen , Yuting Wei , Yuejie Chi

The problem of two-player zero-sum Markov games has recently attracted increasing interests in theoretical studies of multi-agent reinforcement learning (RL). In particular, for finite-horizon episodic Markov decision processes (MDPs), it…

Machine Learning · Computer Science 2024-06-07 Songtao Feng , Ming Yin , Yu-Xiang Wang , Jing Yang , Yingbin Liang

Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments. The original Q-learning suffers from performance and complexity challenges across very large networks. Herein,…

Machine Learning · Computer Science 2024-09-02 Talha Bozkus , Urbashi Mitra

This paper presents the MAXQ approach to hierarchical reinforcement learning based on decomposing the target Markov decision process (MDP) into a hierarchy of smaller MDPs and decomposing the value function of the target MDP into an…

Machine Learning · Computer Science 2007-05-23 Thomas G. Dietterich

The paper introduces the first formulation of convex Q-learning for Markov decision processes with function approximation. The algorithms and theory rest on a relaxation of a dual of Manne's celebrated linear programming characterization of…

Optimization and Control · Mathematics 2023-09-12 Fan Lu , Sean Meyn

For continuing tasks, average cost Markov decision processes have well-documented value and can be solved using efficient algorithms. However, it explicitly assumes that the agent is risk-neutral. In this work, we extend risk-neutral…

Machine Learning · Computer Science 2025-12-23 Weikai Wang , Erick Delage

We propose a new simple and natural algorithm for learning the optimal Q-value function of a discounted-cost Markov Decision Process (MDP) when the transition kernels are unknown. Unlike the classical learning algorithms for MDPs, such as…

Optimization and Control · Mathematics 2019-01-31 Dileep Kalathil , Vivek S. Borkar , Rahul Jain

Robust reinforcement learning (RRL) aims at seeking a robust policy to optimize the worst case performance over an uncertainty set of Markov decision processes (MDPs). This set contains some perturbed MDPs from a nominal MDP (N-MDP) that…

Machine Learning · Computer Science 2023-11-21 Ukjo Hwang , Songnam Hong

This paper presents the first model-free, simulator-free reinforcement learning algorithm for Constrained Markov Decision Processes (CMDPs) with sublinear regret and zero constraint violation. The algorithm is named Triple-Q because it…

Machine Learning · Computer Science 2021-10-26 Honghao Wei , Xin Liu , Lei Ying

We study variance-dependent regret bounds for Markov decision processes (MDPs). Algorithms with variance-dependent regret guarantees can automatically exploit environments with low variance (e.g., enjoying constant regret on deterministic…

Machine Learning · Computer Science 2023-05-23 Runlong Zhou , Zihan Zhang , Simon S. Du
‹ Prev 1 2 3 10 Next ›