Saved in:
Bibliographic Details
Main Authors: Gu, Shangding, Sel, Bilgehan, Ding, Yuhao, Wang, Lu, Lin, Qingwei, Knoll, Alois, Jin, Ming
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.16390
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914812569583616
author Gu, Shangding
Sel, Bilgehan
Ding, Yuhao
Wang, Lu
Lin, Qingwei
Knoll, Alois
Jin, Ming
author_facet Gu, Shangding
Sel, Bilgehan
Ding, Yuhao
Wang, Lu
Lin, Qingwei
Knoll, Alois
Jin, Ming
contents In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints. To tackle this issue, we propose a primal-based framework that orchestrates policy optimization between multi-objective learning and constraint adherence. Our method employs a novel natural policy gradient manipulation method to optimize multiple RL objectives and overcome conflicting gradients between different tasks, since the simple weighted average gradient direction may not be beneficial for specific tasks' performance due to misaligned gradients of different task objectives. When there is a violation of a hard constraint, our algorithm steps in to rectify the policy to minimize this violation. We establish theoretical convergence and constraint violation guarantees in a tabular setting. Empirically, our proposed method also outperforms prior state-of-the-art methods on challenging safe multi-objective reinforcement learning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16390
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
Gu, Shangding
Sel, Bilgehan
Ding, Yuhao
Wang, Lu
Lin, Qingwei
Knoll, Alois
Jin, Ming
Artificial Intelligence
Machine Learning
In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints. To tackle this issue, we propose a primal-based framework that orchestrates policy optimization between multi-objective learning and constraint adherence. Our method employs a novel natural policy gradient manipulation method to optimize multiple RL objectives and overcome conflicting gradients between different tasks, since the simple weighted average gradient direction may not be beneficial for specific tasks' performance due to misaligned gradients of different task objectives. When there is a violation of a hard constraint, our algorithm steps in to rectify the policy to minimize this violation. We establish theoretical convergence and constraint violation guarantees in a tabular setting. Empirically, our proposed method also outperforms prior state-of-the-art methods on challenging safe multi-objective reinforcement learning tasks.
title Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.16390