English
Related papers

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

200 papers

We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove…

Machine Learning · Computer Science 2011-05-02 Shie Mannor , John Tsitsiklis

We propose a vector linear programming formulation for a non-stationary, finite-horizon Markov decision process with vector-valued rewards. Pareto efficient policies are shown to correspond to efficient solutions of the linear program, and…

Optimization and Control · Mathematics 2025-06-02 Anas Mifrani , Dominikus Noll

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

Motion planning under uncertainty for an autonomous system can be formulated as a Markov Decision Process with a continuous state space. In this paper, we propose a novel solution to this decision-theoretic planning problem that directly…

Robotics · Computer Science 2020-07-02 Junhong Xu , Kai Yin , Lantao Liu

The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum.…

Machine Learning · Computer Science 2019-11-13 Mattis Manfred Kämmerer

This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are…

Machine Learning · Computer Science 2018-10-19 Amir Erfan Eshratifar , David Eigen , Massoud Pedram

Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds. We propose a new approximate bilinear programming formulation of value function approximation,…

Artificial Intelligence · Computer Science 2010-06-15 Marek Petrik , Shlomo Zilberstein

In this work, we investigate the optimal control problem for continuous-time Markov decision processes with the random impact of the environment. We provide conditions to show the existence of optimal controls under finite-horizon criteria.…

Optimization and Control · Mathematics 2020-06-23 Jinghai Shao , Kun Zhao

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (or minimize…

Optimization and Control · Mathematics 2015-07-07 Mahmoud El Chamie , Behcet Acikmese

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

A novel Policy Gradient (PG) algorithm, called $\textit{Matryoshka Policy Gradient}$ (MPG), is introduced and studied, in the context of fixed-horizon max-entropy reinforcement learning, where an agent aims at maximizing entropy bonuses…

Machine Learning · Computer Science 2024-10-10 François Ged , Maria Han Veiga

Decision processes with incomplete state feedback have been traditionally modeled as Partially Observable Markov Decision Processes. In this paper, we present an alternative formulation based on probabilistic regular languages. The proposed…

Optimization and Control · Mathematics 2009-08-07 Ishanu Chattopadhyay , Asok Ray

In this paper, we present algorithms that perform gradient ascent of the average reward in a partially observable Markov decision process (POMDP). These algorithms are based on GPOMDP, an algorithm introduced in a companion paper (Baxter…

Artificial Intelligence · Computer Science 2019-11-18 J. Baxter , P. L. Bartlett , L. Weaver

This paper provides new conditions for dynamic optimality in discrete time and uses them to establish fundamental dynamic programming results for several commonly used recursive preference specifications. These include Epstein-Zin…

General Economics · Economics 2020-06-23 Guanlong Ren , John Stachurski

Recent works have shown that gradient-update alignment is a powerful signal for modulating optimizer updates, often leading to faster training. We promote this update-wise heuristic as a mathematically grounded principle for selecting and…

Machine Learning · Computer Science 2026-05-08 Jaerin Lee , Kyoung Mu Lee

In order to compute near-optimal policies with policy-gradient algorithms, it is common in practice to include intrinsic exploration terms in the learning objective. Although the effectiveness of these terms is usually justified by an…

Machine Learning · Computer Science 2025-08-21 Adrien Bolland , Gaspard Lambrechts , Damien Ernst

Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization poses significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon…

Optimization and Control · Mathematics 2026-03-10 Xin Chen , Yifan Hu , Minda Zhao

We consider policy gradient methods for stochastic optimal control problem in continuous time. In particular, we analyze the gradient flow for the control, viewed as a continuous time limit of the policy gradient method. We prove the global…

Optimization and Control · Mathematics 2025-04-15 Mo Zhou , Jianfeng Lu

It is strange but fruitful to think about the functions as random processes. Any function can be viewed as a martingale (in many different ways) with discrete time. But it can be useful to have continuous time too. Processes can emulate…

Probability · Mathematics 2011-06-21 Alexander Volberg

In this paper, we study a Markov chain-based stochastic gradient algorithm in general Hilbert spaces, aiming at approximating the optimal solution of a quadratic loss function. We establish probabilistic upper bounds on its convergence. We…

Machine Learning · Statistics 2025-12-16 Priyanka Roy , Susanne Saminger-Platz