paper-with-me

Papers

Linear programming-based solution methods for constrained partially observable Markov decision processes

2022-06-28 · Robert K. Helmeczi, Can Kavaklioglu, Mucahit Cevik

Constrained partially observable Markov decision processes (CPOMDPs) have been used to model various real-world phenomena. However, they are notoriously difficult to solve to optimality, and there exist only a few approximation methods for obtaining high-quality solutions. In this study, grid-based approximations are used in combination with linear programming (LP) models to generate approximate policies for CPOMDPs. A detailed numerical study is conducted with six CPOMDP problem instances considering both their finite and infinite horizon formulations. The quality of approximation algorithms for solving unconstrained POMDP problems is established through a comparative analysis with exact solution methods. Then, the performance of the LP-based CPOMDP solution approaches for varying budget levels is evaluated. Finally, the flexibility of LP-based approaches is demonstrated by applying deterministic policy constraints, and a detailed investigation into their impact on rewards and CPU run time is provided. For most of the finite horizon problems, deterministic policy constraints are found to have little impact on expected reward, but they introduce a significant increase to CPU run time. For infinite horizon problems, the reverse is observed: deterministic policies tend to yield lower expected total rewards than their stochastic counterparts, but the impact of deterministic constraints on CPU run time is negligible in this case. Overall, these results demonstrate that LP models can effectively generate approximate policies for both finite and infinite horizon problems while providing the flexibility to incorporate various additional constraints into the underlying model.

📄 PDF Abstract BibTeX arXiv:2206.14081

Code (0)

등록된 구현이 없습니다.

Tasks

CPU

Similar Papers 제목 키워드 기반

HSVI can solve zero-sum Partially Observable Stochastic Games

2022-10-26 · Aurélien Delage, Olivier Buffet, Jilles S. Dibangoye, Abdallah Saffidine

State-of-the-art methods for solving 2-player zero-sum imperfect information games rely on linear programming or regret minimization, though not on dynamic programming (DP) or heuristic search (HS), while the latter are …

Decision MakingHeuristic SearchOpen-Ended Question AnsweringSequential Decision Making

Efficient Inference and Structured Learning for Semantic Role Labeling

2015-01-01 · TACL 2015 1 · Oscar T{\"a}ckstr{\"o}m, Kuzman Ganchev, Dipanjan Das

We present a dynamic programming algorithm for efficient constrained inference in semantic role labeling. The algorithm tractably captures a majority of the structural constraints examined by prior work in this area, whi…

Semantic ParsingSemantic Role Labeling

Analysis of approximate linear programming solution to Markov decision problem with log barrier function

2025-09-24 · Donghwan Lee, Hyukjun Yang, Bum Geun Park arxiv

There are two primary approaches to solving Markov decision problems (MDPs): dynamic programming based on the Bellman equation and linear programming (LP). Dynamic programming methods are the most widely used and form th…

Reinforcement LearningOffline RL

A Linear Programming Approach for Resource-Aware Information-Theoretic Tree Abstractions

2022-08-08 · Daniel T. Larsson, Dipankar Maity, Panagiotis Tsiotras

In this chapter, an integer linear programming formulation for the problem of obtaining task-relevant, multi-resolution, environment abstractions for resource-constrained autonomous agents is presented. The formulation l…

Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization

2024-10-03 · Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti

We study online learning in \emph{constrained MDPs} (CMDPs), focusing on the goal of attaining sublinear strong regret and strong cumulative constraint violation. Differently from their standard (weak) counterparts, thes…