English
Related papers

Related papers: Confident Approximate Policy Iteration for Efficie…

200 papers

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

This paper proposes a general incremental policy iteration adaptive dynamic programming (ADP) algorithm for model-free robust optimal control of unknown nonlinear systems. The approach integrates recursive least squares estimation with…

Optimization and Control · Mathematics 2025-09-01 Qingkai Meng , Fenglan Wang , Lin Zhao

This paper presents a constrained adaptive dynamic programming (CADP) algorithm to solve general nonlinear nonaffine optimal control problems with known dynamics. Unlike previous ADP algorithms, it can directly deal with problems with state…

Systems and Control · Electrical Eng. & Systems 2022-04-11 Jingliang Duan , Zhengyu Liu , Shengbo Eben Li , Qi Sun , Zhenzhong Jia , Bo Cheng

Safety is the priority concern when applying reinforcement learning (RL) algorithms to real-world control problems. While policy iteration provides a fundamental algorithm for standard RL, an analogous theoretical algorithm for safe RL…

Machine Learning · Computer Science 2025-03-14 Yujie Yang , Zhilong Zheng , Shengbo Eben Li , Wei Xu , Jingjing Liu , Xianyuan Zhan , Ya-Qin Zhang

Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifies the standard RL…

Machine Learning · Statistics 2019-10-15 Elena Smirnova , Elvis Dohmatob

Solving Markov Decision Processes (MDPs) is a recurrent task in engineering. Even though it is known that solutions for minimizing the infinite horizon expected reward can be found in polynomial time using Linear Programming techniques,…

Computational Complexity · Computer Science 2014-10-29 Romain Hollanders , Balázs Gerencsér , Jean-Charles Delvenne , Raphaël M. Jungers

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

Given a discounted cost, we study deterministic discrete-time systems whose inputs are generated by policy iteration (PI). We provide novel near-optimality and stability properties, while allowing for non stabilizing initial policies. That…

Optimization and Control · Mathematics 2024-03-29 Jonathan de Brusse , Mathieu Granzotto , Romain Postoyan , Dragan Nešić

In this work, we design quantum algorithms that are more efficient than classical algorithms to solve time-dependent and finite-horizon Markov Decision Processes (MDPs) in two distinct settings: (1) In the exact dynamics setting, where the…

Quantum Physics · Physics 2025-08-11 Bin Luo , Yuwen Huang , Jonathan Allcock , Xiaojun Lin , Shengyu Zhang , John C. S. Lui

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

This paper investigates the computational complexity of reinforcement learning in a novel linear function approximation regime, termed partial $q^{\pi}$-realizability. In this framework, the objective is to learn an $\epsilon$-optimal…

Artificial Intelligence · Computer Science 2025-10-31 Shayan Karimi , Xiaoqi Tan

We consider a dynamic programming (DP) approach to approximately solving an infinite-horizon constrained Markov decision process (CMDP) problem with a fixed initial-state for the expected total discounted-reward criterion with a…

Optimization and Control · Mathematics 2023-08-08 Hyeong Soo Chang

Equipping approximate dynamic programming (ADP) with inputconstraints has a tremendous significance. This enables ADP to be applied tothe systems with actuator limitations, which is quite common for dynamicalsystems. In a conventional…

Optimization and Control · Mathematics 2018-05-24 Xuefeng Bao , Zhi-Hong Mao , Nitin Sharma

Bisimulation metrics define a distance measure between states of a Markov decision process (MDP) based on a comparison of reward sequences. Due to this property they provide theoretical guarantees in value function approximation (VFA). In…

Machine Learning · Computer Science 2022-11-15 Mete Kemertas , Allan Jepson

In this paper we propose a novel algorithm, factored value iteration (FVI), for the approximate solution of factored Markov decision processes (fMDPs). The traditional approximate value iteration algorithm is modified in two ways. For one,…

Artificial Intelligence · Computer Science 2008-08-13 Istvan Szita , Andras Lorincz

Recent progress in randomized motion planners has led to the development of a new class of sampling-based algorithms that provide asymptotic optimality guarantees, notably the RRT* and the PRM* algorithms. Careful analysis reveals that the…

Robotics · Computer Science 2016-09-21 Oktay Arslan , Panagiotis Tsiotras

We consider the problem of controlling a fully specified Markov decision process (MDP), also known as the planning problem, when the state space is very large and calculating the optimal policy is intractable. Instead, we pursue the more…

Optimization and Control · Mathematics 2019-01-09 Yasin Abbasi-Yadkori , Peter L. Bartlett , Xi Chen , Alan Malek

We introduce Reliable Policy Iteration (RPI) and Conservative RPI (CRPI), variants of Policy Iteration (PI) and Conservative PI (CPI), that retain tabular guarantees under function approximation. RPI uses a novel Bellman-constrained…

Machine Learning · Computer Science 2026-04-03 S. R. Eshwar , Gugan Thoppe , Ananyabrata Barua , Aditya Gopalan , Gal Dalal

We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability regret bound of…

Machine Learning · Computer Science 2026-02-17 Orin Levy , Aviv Rosenberg , Alon Cohen , Yishay Mansour

We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in time, almost surely. Although Markovian policies are no…

Machine Learning · Computer Science 2024-06-14 Jeremy McMahan , Xiaojin Zhu