Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: McMahan, Jeremy
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914999001153536
author McMahan, Jeremy
author_facet McMahan, Jeremy
contents We present a novel algorithm that efficiently computes near-optimal deterministic policies for constrained reinforcement learning (CRL) problems. Our approach combines three key ideas: (1) value-demand augmentation, (2) action-space approximate dynamic programming, and (3) time-space rounding. Our algorithm constitutes a fully polynomial-time approximation scheme (FPTAS) for any time-space recursive (TSR) cost criteria. A TSR criteria requires the cost of a policy to be computable recursively over both time and (state) space, which includes classical expectation, almost sure, and anytime constraints. Our work answers three open questions spanning two long-standing lines of research: polynomial-time approximability is possible for 1) anytime-constrained policies, 2) almost-sure-constrained policies, and 3) deterministic expectation-constrained policies.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14183
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time
McMahan, Jeremy
Machine Learning
Data Structures and Algorithms
We present a novel algorithm that efficiently computes near-optimal deterministic policies for constrained reinforcement learning (CRL) problems. Our approach combines three key ideas: (1) value-demand augmentation, (2) action-space approximate dynamic programming, and (3) time-space rounding. Our algorithm constitutes a fully polynomial-time approximation scheme (FPTAS) for any time-space recursive (TSR) cost criteria. A TSR criteria requires the cost of a policy to be computable recursively over both time and (state) space, which includes classical expectation, almost sure, and anytime constraints. Our work answers three open questions spanning two long-standing lines of research: polynomial-time approximability is possible for 1) anytime-constrained policies, 2) almost-sure-constrained policies, and 3) deterministic expectation-constrained policies.
title Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time
topic Machine Learning
Data Structures and Algorithms
url https://arxiv.org/abs/2405.14183