English
Related papers

Related papers: Classical Policy Gradient: Preserving Bellman's Pr…

200 papers

This paper considers non-smooth optimization problems where we seek to minimize the pointwise maximum of a continuously parameterized family of functions. Since the objective function is given as the solution to a maximization problem,…

Optimization and Control · Mathematics 2026-01-12 Dimitris Boskos , Jorge Cortés , Sonia Martínez

In this paper, we propose a policy gradient method for confounded partially observable Markov decision processes (POMDPs) with continuous state and observation spaces in the offline setting. We first establish a novel identification result…

Machine Learning · Statistics 2023-12-04 Mao Hong , Zhengling Qi , Yanxun Xu

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

In this paper, we consider discrete-time infinite horizon problems of optimal control to a terminal set of states. These are the problems that are often taken as the starting point for adaptive dynamic programming. Under very general…

Systems and Control · Computer Science 2015-10-05 Dimitri P. Bertsekas

We consider a risk-sensitive continuous-time Markov decision process over a finite time duration. Under the conditions that can be satisfied by unbounded transition and cost rates, we show the existence of an optimal policy, and the…

Optimization and Control · Mathematics 2018-11-29 Xin Guo , Qiuli Liu , Yi Zhang

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

In this paper, we develop a scaled gradient-momentum framework for continuous-time optimization that achieves global finite-time convergence. A state-dependent scaling mechanism is introduced to enable classical dynamics, such as…

Optimization and Control · Mathematics 2026-04-15 Yu Zhou , Mengmou Li , Masaaki Nagahara

Motivated by emerging applications in machine learning, we consider an optimization problem in a general form where the gradient of the objective function is available through a biased stochastic oracle. We assume a bias-control parameter…

Optimization and Control · Mathematics 2026-02-10 Yin Liu , Sam Davanloo Tajbakhsh

The goal of this paper is to analyze distributional Markov Decision Processes as a class of control problems in which the objective is to learn policies that steer the distribution of a cumulative reward toward a prescribed target law,…

Optimization and Control · Mathematics 2026-02-09 Nicole Bäuerle , Athanasios Vasileiadis

We propose policy gradient algorithms for robust infinite-horizon Markov decision processes (MDPs) with non-rectangular uncertainty sets, thereby addressing an open challenge in the robust MDP literature. Indeed, uncertainty sets that…

Optimization and Control · Mathematics 2025-09-30 Mengmeng Li , Daniel Kuhn , Tobias Sutter

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

Machine Learning · Computer Science 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

We study optimality for the safety-constrained Markov decision process which is the underlying framework for safe reinforcement learning. Specifically, we consider a constrained Markov decision process (with finite states and finite…

Systems and Control · Electrical Eng. & Systems 2023-07-13 Rahul Misra , Rafał Wisniewski , Carsten Skovmose Kallesøe

Hybrid quantum-classical optimization algorithms represent one of the most promising application for near-term quantum computers. In these algorithms the goal is to optimize an observable quantity with respect to some classical parameters,…

Quantum Physics · Physics 2021-01-27 Leonardo Banchi , Gavin E. Crooks

In this paper, we consider the risk-sensitive cost criterion with exponentiated costs for Markov decision processes and develop a model-free policy gradient algorithm in this setting. Unlike additive cost criteria such as average or…

Machine Learning · Computer Science 2025-08-05 Soumyajit Guin , Vivek S. Borkar , Shalabh Bhatnagar

We revisit the Reinforce policy gradient algorithm from the literature. Note that this algorithm typically works with cost returns obtained over random length episodes obtained from either termination upon reaching a goal state (as with…

Machine Learning · Computer Science 2023-10-10 Shalabh Bhatnagar

In this paper we propose a novel gradient algorithm to learn a policy from an expert's observed behavior assuming that the expert behaves optimally with respect to some unknown reward function of a Markovian Decision Problem. The…

Machine Learning · Computer Science 2012-06-26 Gergely Neu , Csaba Szepesvari

The policy gradient theorem describes the gradient of the expected discounted return with respect to an agent's policy parameters. However, most policy gradient methods drop the discount factor from the state distribution and therefore do…

Machine Learning · Computer Science 2020-03-02 Chris Nota , Philip S. Thomas

While the optimization landscape of policy gradient methods has been recently investigated for partially observed linear systems in terms of both static output feedback and dynamical controllers, they only provide convergence guarantees to…

Optimization and Control · Mathematics 2023-04-25 Feiran Zhao , Xingyun Fu , Keyou You

Arising in semi-parametric statistics, control applications, and as sub-problems in global optimization methods, certain optimization problems can have objective functions requiring numerical integration to evaluate, yet gradient function…

Optimization and Control · Mathematics 2025-03-06 Christian Varner , Vivak Patel

Many engineering problems have multiple objectives, and the overall aim is to optimize a non-linear function of these objectives. In this paper, we formulate the problem of maximizing a non-linear concave function of multiple long-term…

Machine Learning · Computer Science 2025-09-23 Qinbo Bai , Mridul Agarwal , Vaneet Aggarwal