paper-with-me

Papers

Towards a Practical Understanding of Lagrangian Methods in Safe Reinforcement Learning

2025-10-20 · Lindsay Spoor, Álvaro Serra-Gómez, Aske Plaat, Thomas Moerland arxiv

Safe reinforcement learning addresses constrained optimization problems where maximizing performance must be balanced against safety constraints, and Lagrangian methods are a widely used approach for this purpose. However, the effectiveness of Lagrangian methods depends crucially on the choice of the Lagrange multiplier $λ$, which governs the multi-objective trade-off between return and cost. A common practice is to update the multiplier automatically during training. Although this approach is standard in practice, there remains limited empirical evidence on the optimally achievable trade-off between return and cost as a function of $λ$, and there is currently no systematic benchmark comparing automated update mechanisms to this empirical optimum. Therefore, we study (i) the constraint geometry for eight widely used safety tasks and (ii) the previously overlooked constraint-regime sensitivity of different Lagrange multiplier update mechanisms in safe reinforcement learning. Through the lens of multi-objective analysis, we present empirical Pareto frontiers that offer a complete visualization of the trade-off between return and cost in the underlying optimization problem. Our results reveal the highly sensitive nature of $λ$ and further show that the restrictiveness of the constraint cost can vary across different cost limits within the same task. This highlights the importance of careful cost limit selection across different regions of cost restrictiveness when evaluating safe reinforcement learning methods. We provide a recommended set of cost limits for each evaluated task and offer an open-source code base: https://github.com/lindsayspoor/Lagrangian_SafeRL.

📄 PDF Abstract BibTeX arXiv:2510.17564

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Adaptive Primal-Dual Method for Safe Reinforcement Learning

2024-02-01 · Weiqin Chen, James Onyejizu, Long Vu, Lan Hoang 외

Primal-dual methods have a natural application in Safe Reinforcement Learning (SRL), posed as a constrained policy optimization problem. In practice however, applying primal-dual methods to SRL is challenging, due to the…

reinforcement-learningReinforcement LearningSafe Reinforcement Learning

Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian

2021-08-26 · Baiyu Peng, Jingliang Duan, Jianyu Chen, Shengbo Eben Li 외

Safety is essential for reinforcement learning (RL) applied in the real world. Adding chance constraints (or probabilistic constraints) is a suitable way to enhance RL safety under uncertainty. Existing chance-constraine…

reinforcement-learningReinforcement Learning (RL)Robot Navigation

Enhance the Safety in Reinforcement Learning by ADRC Lagrangian Methods

2026-01-26 · Mingxu Zhang, Huicheng Zhang, Jiaming Ji, Yaodong Yang 외 arxiv

Safe reinforcement learning (Safe RL) seeks to maximize rewards while satisfying safety constraints, typically addressed through Lagrangian-based methods. However, existing approaches, including PID and classical Lagrang…

Reinforcement Learning

Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes

2023-06-12 · Adrian Müller, Pragnya Alatur, Giorgia Ramponi, Niao He

Constrained Markov Decision Processes (CMDPs) are one of the common ways to model safe reinforcement learning problems, where constraint functions model the safety objectives. Lagrangian-based dual or primal-dual algorit…

Safe Reinforcement Learning

Responsive Safety in Reinforcement Learning by PID Lagrangian Methods

2020-07-08 · Adam Stooke, Joshua Achiam, Pieter Abbeel

Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe reinforcement learning, leads to constraint-…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning