English
Related papers

Related papers: Regret Analysis of Policy Gradient Algorithm for I…

200 papers

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 show the convergence rates of posterior distributions of the model dynamics in a MDP for both episodic and continuous tasks. The theoretical results hold for general state and action space and the parameter space of the…

Statistics Theory · Mathematics 2019-07-23 Zhen Li , Eric Laber

We introduce learning and planning algorithms for average-reward MDPs, including 1) the first general proven-convergent off-policy model-free control algorithm without reference states, 2) the first proven-convergent off-policy model-free…

Machine Learning · Computer Science 2021-06-29 Yi Wan , Abhishek Naik , Richard S. Sutton

We investigate online Markov Decision Processes (MDPs) with adversarially changing loss functions and known transitions. We choose dynamic regret as the performance measure, defined as the performance difference between the learner and any…

Machine Learning · Computer Science 2022-08-29 Peng Zhao , Long-Fei Li , Zhi-Hua Zhou

While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will…

Machine Learning · Computer Science 2020-07-16 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta

Recent studies have shown that episodic reinforcement learning (RL) is no harder than bandits when the total reward is bounded by $1$, and proved regret bounds that have a polylogarithmic dependence on the planning horizon $H$. However, it…

Machine Learning · Computer Science 2023-05-16 Kaixuan Ji , Qingyue Zhao , Jiafan He , Weitong Zhang , Quanquan Gu

Many control problems in environments that can be modeled as Markov decision processes (MDPs) concern infinite-time horizon specifications. The classical aim in this context is to compute a control policy that maximizes the probability of…

Systems and Control · Computer Science 2017-05-03 Ruediger Ehlers , Salar Moarref , Ufuk Topcu

State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered…

Machine Learning · Computer Science 2019-11-01 Yonathan Efroni , Nadav Merlis , Mohammad Ghavamzadeh , Shie Mannor

We prove new upper and lower bounds for sample complexity of finding an $\epsilon$-optimal policy of an infinite-horizon average-reward Markov decision process (MDP) given access to a generative model. When the mixing time of the…

Machine Learning · Computer Science 2021-06-15 Yujia Jin , Aaron Sidford

In this paper, we study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. The multi-batch reinforcement learning framework, where the agent…

Machine Learning · Computer Science 2022-10-18 Zihan Zhang , Yuhang Jiang , Yuan Zhou , Xiangyang Ji

We consider the problem of learning in episodic finite-horizon Markov decision processes with an unknown transition function, bandit feedback, and adversarial losses. We propose an efficient algorithm that achieves…

Machine Learning · Computer Science 2020-11-03 Chi Jin , Tiancheng Jin , Haipeng Luo , Suvrit Sra , Tiancheng Yu

Many policy-based reinforcement learning (RL) algorithms can be viewed as instantiations of approximate policy iteration (PI), i.e., where policy improvement and policy evaluation are both performed approximately. In applications where the…

Machine Learning · Computer Science 2023-06-29 Yashaswini Murthy , Mehrdad Moharrami , R. Srikant

In this paper we present an algorithm to compute risk averse policies in Markov Decision Processes (MDP) when the total cost criterion is used together with the average value at risk (AVaR) metric. Risk averse policies are needed when large…

Optimization and Control · Mathematics 2016-02-17 Stefano Carpin , Yin-Lam Chow , Marco Pavone

Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Mean payoff (or long-run average reward) provides a mathematically elegant formalism to express performance related…

Performance · Computer Science 2017-09-08 Jan Křetínský , Tobias Meggendorfer

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

We study non-rectangular robust Markov decision processes under the average-reward criterion, where the ambiguity set couples transition probabilities across states and the adversary commits to a stationary kernel for the entire horizon. We…

Optimization and Control · Mathematics 2026-03-11 Shengbo Wang , Nian Si

We develop several provably efficient model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov Decision Processes (MDPs). We consider both online setting and the setting with access to a simulator. In the…

Machine Learning · Computer Science 2023-06-29 Zihan Zhang , Qiaomin Xie

Hierarchical Reinforcement Learning (HRL) approaches have shown successful results in solving a large variety of complex, structured, long-horizon problems. Nevertheless, a full theoretical understanding of this empirical evidence is…

Machine Learning · Computer Science 2025-02-05 Gianluca Drappo , Alberto Maria Metelli , Marcello Restelli

In this paper, we study reinforcement learning in Markov Decision Processes with Probabilistic Reward Machines (PRMs), a form of non-Markovian reward commonly found in robotics tasks. We design an algorithm for PRMs that achieves a regret…

Machine Learning · Statistics 2024-08-21 Xiaofeng Lin , Xuezhou Zhang

Actor-Critic methods are widely used for their scalability, yet existing theoretical guarantees for infinite-horizon average-reward Markov Decision Processes (MDPs) often rely on restrictive ergodicity assumptions. We propose NAC-B, a…

Machine Learning · Computer Science 2025-10-28 Swetha Ganesh , Vaneet Aggarwal