English
Related papers

Related papers: Improved bound on the worst case complexity of Pol…

200 papers

Several recent works have proposed instance-dependent upper bounds on the number of episodes needed to identify, with probability $1-\delta$, an $\varepsilon$-optimal policy in finite-horizon tabular Markov Decision Processes (MDPs). These…

Machine Learning · Statistics 2023-11-13 Aymen Al-Marjani , Andrea Tirinzoni , Emilie Kaufmann

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

This paper addresses the challenge of solving Constrained Markov Decision Processes (CMDPs) with $d > 1$ constraints when the transition dynamics are unknown, but samples can be drawn from a generative model. We propose a model-based…

Machine Learning · Computer Science 2025-03-11 Max Buckley , Konstantinos Papathanasiou , Andreas Spanopoulos

Markov decision processes (MDPs) and simple stochastic games (SSGs) provide a rich mathematical framework to study many important problems related to probabilistic systems. MDPs and SSGs with finite-horizon objectives, where the goal is to…

Computer Science and Game Theory · Computer Science 2012-09-18 Krishnendu Chatterjee , Rasmus Ibsen-Jensen

The standard version of the policy iteration (PI) algorithm fails for semicontinuous models, that is, for models with lower semicontinuous one-step costs and weakly continuous transition law. This is due to the lack of continuity properties…

Optimization and Control · Mathematics 2023-07-17 Óscar Vega-Amaya , Fernando Luque-Vásquez

In this paper, we consider reinforcement learning of Markov Decision Processes (MDP) with peak constraints, where an agent chooses a policy to optimize an objective and at the same time satisfy additional constraints. The agent has to take…

Optimization and Control · Mathematics 2019-12-09 Ather Gattami

Deterministic Markov Decision Processes (DMDPs) are a mathematical framework for decision-making where the outcomes and future possible actions are deterministically determined by the current action taken. DMDPs can be viewed as a finite…

Artificial Intelligence · Computer Science 2025-06-17 Ali Asadi , Krishnendu Chatterjee , Jakob de Raaij

Value iteration is a well-known method of solving Markov Decision Processes (MDPs) that is simple to implement and boasts strong theoretical convergence guarantees. However, the computational cost of value iteration quickly becomes…

Machine Learning · Computer Science 2021-07-26 Guanting Chen , Johann Demetrio Gaebler , Matt Peng , Chunlin Sun , Yinyu Ye

Calculating optimal policies is known to be computationally difficult for Markov decision processes (MDPs) with Borel state and action spaces. This paper studies finite-state approximations of discrete time Markov decision processes with…

Optimization and Control · Mathematics 2016-09-23 Naci Saldi , Serdar Yüksel , Tamás Linder

We study the problem of learning policies that maximize cumulative reward while satisfying safety constraints, even when the real environment differs from a simulator or nominal model. We focus on robust constrained Markov decision…

Machine Learning · Computer Science 2025-11-12 Sourav Ganguly , Arnob Ghosh

Modified policy iteration (MPI) is a dynamic programming algorithm that combines elements of policy iteration and value iteration. The convergence of MPI has been well studied in the context of discounted and average-cost MDPs. In this…

Machine Learning · Computer Science 2024-02-16 Yashaswini Murthy , Mehrdad Moharrami , R. Srikant

This work considers the sample complexity of obtaining an $\varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP), given access to a generative model (simulator). When the ground-truth MDP is weakly communicating,…

Machine Learning · Computer Science 2022-12-02 Jinghan Wang , Mengdi Wang , Lin F. Yang

We study upper and lower bounds on the sample-complexity of learning near-optimal behaviour in finite-state discounted Markov Decision Processes (MDPs). For the upper bound we make the assumption that each action leads to at most two…

Machine Learning · Computer Science 2013-05-17 Tor Lattimore , Marcus Hutter

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm…

Machine Learning · Computer Science 2011-09-09 Mohammad Gheshlaghi Azar , Vicenc Gomez , Hilbert J. Kappen

Recently discovered polyhedral structures of the value function for finite state-action discounted Markov decision processes (MDP) shed light on understanding the success of reinforcement learning. We investigate the value function polytope…

Machine Learning · Computer Science 2022-06-27 Yue Wu , Jesús A. De Loera

In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to identify an $\epsilon$-optimal policy with probability $1-\delta$. While minimax optimal algorithms exist for this problem, its instance-dependent…

Machine Learning · Computer Science 2022-10-25 Andrea Tirinzoni , Aymen Al-Marjani , Emilie Kaufmann

The proximal policy optimization (PPO) algorithm stands as one of the most prosperous methods in the field of reinforcement learning (RL). Despite its success, the theoretical understanding of PPO remains deficient. Specifically, it is…

Machine Learning · Computer Science 2023-06-09 Han Zhong , Tong Zhang

We build on a recently introduced geometric interpretation of Markov Decision Processes (MDPs) to analyze classical MDP-solving algorithms: Value Iteration (VI) and Policy Iteration (PI). First, we develop a geometry-based analytical…

Machine Learning · Computer Science 2025-03-07 Arsenii Mustafin , Aleksei Pakharev , Alex Olshevsky , Ioannis Ch. Paschalidis

We resolve the open question regarding the sample complexity of policy learning for maximizing the long-run average reward associated with a uniformly ergodic Markov decision process (MDP), assuming a generative model. In this context, the…

Machine Learning · Computer Science 2024-02-14 Shengbo Wang , Jose Blanchet , Peter Glynn

Markov decision processes (MDPs) are used to model stochastic systems in many applications. Several efficient algorithms to compute optimal policies have been studied in the literature, including value iteration (VI) and policy iteration.…

Optimization and Control · Mathematics 2021-08-30 Vineet Goyal , Julien Grand-Clement