English
Related papers

Related papers: Beyond Bellman: High-Order Generator Regression fo…

200 papers

We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several…

Machine Learning · Computer Science 2018-03-30 Huizhen Yu

We study the policy iteration algorithm (PIA) for entropy-regularized stochastic control problems on an infinite time horizon with a large discount rate, focusing on two main scenarios. First, we analyze PIA with bounded coefficients where…

Optimization and Control · Mathematics 2025-05-28 Hung Vinh Tran , Zhenhua Wang , Yuming Paul Zhang

Polynomial regression is widely used and can help to express nonlinear patterns. However, considering very high polynomial orders may lead to overfitting and poor extrapolation ability for unseen data. The paper presents a method for…

Machine Learning · Computer Science 2023-08-01 Andrei Ivanov , Stefan Maria Ailuro

Many real-world control problems, ranging from finance to robotics, evolve in continuous time with non-uniform, event-driven decisions. Standard discrete-time reinforcement learning (RL), based on fixed-step Bellman updates, struggles in…

Machine Learning · Computer Science 2026-02-17 Minh Nguyen

Reliable long-horizon value prediction is difficult in offline reinforcement learning because fitted value methods combine bootstrapping, function approximation, and distribution shift, while standard guarantees often require Bellman…

Machine Learning · Statistics 2026-05-11 Lars van der Laan , Nathan Kallus

Ordinal regression is a classification task where classes have an order and prediction error increases the further the predicted class is from the true class. The standard approach for modeling ordinal data involves fitting parallel…

Machine Learning · Computer Science 2022-02-16 Fred Lu , Francis Ferraro , Edward Raff

We study the policy evaluation problem in multi-agent reinforcement learning where a group of agents, with jointly observed states and private local actions and rewards, collaborate to learn the value function of a given policy via local…

Optimization and Control · Mathematics 2021-11-08 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

We present an accelerated algorithm for the solution of static Hamilton-Jacobi-Bellman equations related to optimal control problems. Our scheme is based on a classic policy iteration procedure, which is known to have superlinear…

Optimization and Control · Mathematics 2016-02-22 Alessandro Alla , Maurizio Falcone , Dante Kalise

We consider discrete-time infinite horizon deterministic optimal control problems with nonnegative cost per stage, and a destination that is cost-free and absorbing. The classical linear-quadratic regulator problem is a special case. Our…

Optimization and Control · Mathematics 2017-12-20 Dimitri P. Bertsekas

Offline reinforcement learning promises policy improvement from logged interaction data alone, yet state-of-the-art algorithms remain vulnerable to value over-estimation and to violations of domain knowledge such as monotonicity or…

Systems and Control · Electrical Eng. & Systems 2025-06-18 Ali Baheri

We propose a machine learning algorithm for solving finite-horizon stochastic control problems based on a deep neural network representation of the optimal policy functions. The algorithm has three features: (1) It can solve…

General Economics · Economics 2024-12-09 Xianhua Peng , Steven Kou , Lekang Zhang

We present a computer-checked generic implementation for solving finite-horizon sequential decision problems. This is a wide class of problems, including inter-temporal optimizations, knapsack, optimal bracketing, scheduling, etc. The…

Logic in Computer Science · Computer Science 2023-06-22 Nicola Botta , Patrik Jansson , Cezar Ionescu , David R. Christiansen , Edwin Brady

We consider off-policy temporal-difference (TD) learning in discounted Markov decision processes, where the goal is to evaluate a policy in a model-free way by using observations of a state process generated without executing the policy. To…

Machine Learning · Computer Science 2018-11-27 Huizhen Yu , A. Rupam Mahmood , Richard S. Sutton

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

Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is especially observed in many widely popular policy gradient…

Machine Learning · Computer Science 2020-08-04 Samuele Tosatto , Joao Carvalho , Hany Abdulsamad , Jan Peters

Despite its popularity in the reinforcement learning community, a provably convergent policy gradient method for continuous space-time control problems with nonlinear state dynamics has been elusive. This paper proposes proximal gradient…

Optimization and Control · Mathematics 2022-12-27 Christoph Reisinger , Wolfgang Stockinger , Yufei Zhang

The synthesis of adaptive gain-scheduling controller is discussed for continuous-time linear models characterized by polytopic uncertainties. The proposed approach computes the control law assuming the parameters as uncertain and adaptively…

Systems and Control · Electrical Eng. & Systems 2025-06-17 Ariany C. Oliveira , Victor C. S. Campos , Leonardo. A. Mozelli

Continuous-time stochastic processes underlie many natural and engineered systems. In healthcare, autonomous driving, and industrial control, direct interaction with the environment is often unsafe or impractical, motivating offline…

Machine Learning · Statistics 2025-11-14 Nicolas Hoischen , Petar Bevanda , Max Beier , Stefan Sosnowski , Boris Houska , Sandra Hirche

Most of the policy evaluation algorithms are based on the theories of Bellman Expectation and Optimality Equation, which derive two popular approaches - Policy Iteration (PI) and Value Iteration (VI). However, multi-step bootstrapping is…

Machine Learning · Computer Science 2021-12-16 Yuhui Wang , Qingyuan Wu , Pengcheng He , Xiaoyang Tan

We consider policy evaluation in infinite-horizon discounted Markov decision problems (MDPs) with infinite spaces. We reformulate this task a compositional stochastic program with a function-valued decision variable that belongs to a…

Optimization and Control · Mathematics 2020-05-19 Alec Koppel , Garrett Warnell , Ethan Stump , Peter Stone , Alejandro Ribeiro