English
Related papers

Related papers: Experiments with Infinite-Horizon, Policy-Gradient…

200 papers

We propose new sequential simulation-optimization algorithms for general convex optimization via simulation problems with high-dimensional discrete decision space. The performance of each choice of discrete decision variables is evaluated…

Optimization and Control · Mathematics 2022-02-15 Haixiang Zhang , Zeyu Zheng , Javad Lavaei

Many processes, such as discrete event systems in engineering or population dynamics in biology, evolve in discrete space and continuous time. We consider the problem of optimal decision making in such discrete state and action space…

Machine Learning · Computer Science 2020-10-27 Bastian Alt , Matthias Schultheis , Heinz Koeppl

This work develops novel strategies for optimal planning with semantic observations using continuous state partially observable markov decision processes (CPOMDPs). Two major innovations are presented in relation to Gaussian mixture (GM)…

Artificial Intelligence · Computer Science 2019-08-09 Luke Burks , Ian Loefgren , Nisar Ahmed

This paper focuses on solving a stochastic saddle point problem (SPP) under an overparameterized regime for the case, when the gradient computation is impractical. As an intermediate step, we generalize Same-sample Stochastic Extra-gradient…

Optimization and Control · Mathematics 2024-06-05 Ekaterina Statkevich , Sofiya Bondar , Darina Dvinskikh , Alexander Gasnikov , Aleksandr Lobanov

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

We consider a finite-state partially observable Markov decision problem (POMDP) with an infinite horizon and a discounted cost, and we propose a new method for computing a cost function approximation that is based on features and…

Systems and Control · Electrical Eng. & Systems 2025-07-08 Yuchao Li , Kim Hammar , Dimitri Bertsekas

Stochastic gradient descent procedures have gained popularity for parameter estimation from large data sets. However, their statistical properties are not well understood, in theory. And in practice, avoiding numerical instability requires…

Methodology · Statistics 2016-09-29 Panos Toulis , Edoardo M. Airoldi

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

POMDPs capture a broad class of decision making problems, but hardness results suggest that learning is intractable even in simple settings due to the inherent partial observability. However, in many realistic problems, more information is…

Machine Learning · Computer Science 2023-02-07 Jonathan N. Lee , Alekh Agarwal , Christoph Dann , Tong Zhang

Autonomous systems are often required to operate in partially observable environments. They must reliably execute a specified objective even with incomplete information about the state of the environment. We propose a methodology to…

Artificial Intelligence · Computer Science 2020-01-14 Maxime Bouton , Jana Tumova , Mykel J. Kochenderfer

Partially Observable Markov Decision Processes (POMDPs) model decision making under uncertainty. While there are many approaches to approximately solving POMDPs, we aim to address the problem of learning such models. In particular, we are…

Artificial Intelligence · Computer Science 2025-05-13 Aidan Curtis , Hao Tang , Thiago Veloso , Kevin Ellis , Joshua Tenenbaum , Tomás Lozano-Pérez , Leslie Pack Kaelbling

In constrained Markov decision processes (CMDPs) with adversarial rewards and constraints, a well-known impossibility result prevents any algorithm from attaining both sublinear regret and sublinear constraint violation, when competing…

Machine Learning · Computer Science 2024-09-27 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

In this paper, we investigate a general class of stochastic gradient descent (SGD) algorithms, called Conditioned SGD, based on a preconditioning of the gradient direction. Using a discrete-time approach with martingale tools, we establish…

Statistics Theory · Mathematics 2023-10-17 Rémi Leluc , François Portier

Stochastic coordinate descent algorithms are efficient methods in which each iterate is obtained by fixing most coordinates at their values from the current iteration, and approximately minimizing the objective with respect to the remaining…

Machine Learning · Statistics 2025-04-02 Eméric Gbaguidi

Markov Decision Processes (MDPs) are a popular class of models suitable for solving control decision problems in probabilistic reactive systems. We consider parametric MDPs (pMDPs) that include parameters in some of the transition…

Logic in Computer Science · Computer Science 2018-06-14 Sebastian Arming , Ezio Bartocci , Krishnendu Chatterjee , Joost-Pieter Katoen , Ana Sokolova

Most exact algorithms for general partially observable Markov decision processes (POMDPs) use a form of dynamic programming in which a piecewise-linear and convex representation of one value function is transformed into another. We examine…

Artificial Intelligence · Computer Science 2013-02-08 Anthony R. Cassandra , Michael L. Littman , Nevin Lianwen Zhang

We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we…

Machine Learning · Computer Science 2023-12-15 Sanghyun Son , Laura Yu Zheng , Ryan Sullivan , Yi-Ling Qiao , Ming C. Lin

Modern large-scale statistical models require to estimate thousands to millions of parameters. This is often accomplished by iterative algorithms such as gradient descent, projected gradient descent or their accelerated versions. What are…

Machine Learning · Statistics 2020-03-04 Michael Celentano , Andrea Montanari , Yuchen Wu

The agent learns to organize decision behavior to achieve a behavioral goal, such as reward maximization, and reinforcement learning is often used for this optimization. Learning an optimal behavioral strategy is difficult under the…

Machine Learning · Computer Science 2023-05-09 Kazuki Takahashi , Tomoki Fukai , Yutaka Sakai , Takashi Takekawa

Partially Observable Markov Decision Processes (POMDPs) are used to model environments where the full state cannot be perceived by an agent. As such the agent needs to reason taking into account the past observations and actions. However,…

Machine Learning · Computer Science 2023-10-27 Raphael Avalos , Florent Delgrange , Ann Nowé , Guillermo A. Pérez , Diederik M. Roijers