中文
相关论文

相关论文: Towards a Practical Understanding of Lagrangian Me…

200 篇论文

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-violating behavior…

最优化与控制 · 数学 2020-07-09 Adam Stooke , Joshua Achiam , Pieter Abbeel

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 Lagrangian methods, suffer…

机器学习 · 计算机科学 2026-01-27 Mingxu Zhang , Huicheng Zhang , Jiaming Ji , Yaodong Yang , Ying Sun

The naive application of Reinforcement Learning algorithms to continuous control problems -- such as locomotion and manipulation -- often results in policies which rely on high-amplitude, high-frequency control signals, known colloquially…

机器人学 · 计算机科学 2019-02-14 Steven Bohez , Abbas Abdolmaleki , Michael Neunert , Jonas Buchli , Nicolas Heess , Raia Hadsell

Constrained optimization is popularly seen in reinforcement learning for addressing complex control tasks. From the perspective of dynamic system, iteratively solving a constrained optimization problem can be framed as the temporal…

机器学习 · 计算机科学 2025-01-28 Tianqi Zhang , Puzhen Yuan , Guojian Zhan , Ziyu Lin , Yao Lyu , Zhenzhi Qin , Jingliang Duan , Liping Zhang , Shengbo Eben Li

Safe Reinforcement Learning (Safe RL) is one of the prevalently studied subcategories of trial-and-error-based methods with the intention to be deployed on real-world systems. In safe RL, the goal is to maximize reward performance while…

机器学习 · 计算机科学 2024-08-16 Homayoun Honari , Amir Mehdi Soufi Enayati , Mehran Ghafarian Tamizi , Homayoun Najjaran

In this paper, we consider the linear programming (LP) formulation for deep reinforcement learning. The number of the constraints depends on the size of state and action spaces, which makes the problem intractable in large or continuous…

最优化与控制 · 数学 2021-05-21 Yongfeng Li , Mingming Zhao , Weijie Chen , Zaiwen Wen

Incorporating safety is an essential prerequisite for broadening the practical applications of reinforcement learning in real-world scenarios. To tackle this challenge, Constrained Markov Decision Processes (CMDPs) are leveraged, which…

机器学习 · 计算机科学 2023-11-03 Jaafar Mhamed , Shangding Gu

Online safe reinforcement learning (RL) involves training a policy that maximizes task efficiency while satisfying constraints via interacting with the environments. In this paper, our focus lies in addressing the complex challenges…

机器学习 · 计算机科学 2023-12-27 Yihang Yao , Zuxin Liu , Zhepeng Cen , Peide Huang , Tingnan Zhang , Wenhao Yu , Ding Zhao

Lagrangian relaxation is a versatile mathematical technique employed to relax constraints in an optimization problem, enabling the generation of dual bounds to prove the optimality of feasible solutions and the design of efficient…

人工智能 · 计算机科学 2023-12-25 Augustin Parjadis , Quentin Cappart , Bistra Dilkina , Aaron Ferber , Louis-Martin Rousseau

This paper proposes a safe reinforcement learning (RL) algorithm that approximately solves the state-constrained optimal control problem for continuous-time uncertain nonlinear systems. We formulate the safe RL problem as the minimization…

系统与控制 · 电气工程与系统科学 2025-06-26 Soutrik Bandyopadhyay , Shubhendu Bhasin

In this paper, we study the learning of safe policies in the setting of reinforcement learning problems. This is, we aim to control a Markov Decision Process (MDP) of which we do not know the transition probabilities, but we have access to…

系统与控制 · 电气工程与系统科学 2022-01-14 Santiago Paternain , Miguel Calvo-Fullana , Luiz F. O. Chamon , Alejandro Ribeiro

We examine online safe multi-agent reinforcement learning using constrained Markov games in which agents compete by maximizing their expected total rewards under a constraint on expected total utilities. Our focus is confined to an episodic…

机器学习 · 计算机科学 2023-06-02 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

Offline Preference-based Reinforcement Learning (PbRL) learns rewards and policies aligned with human preferences without the need for extensive reward engineering and direct interaction with human annotators. However, ensuring safety…

人工智能 · 计算机科学 2025-12-24 Ze Gong , Pradeep Varakantham , Akshat Kumar

A large number of objectives have been proposed to train latent variable generative models. We show that many of them are Lagrangian dual functions of the same primal optimization problem. The primal problem optimizes the mutual information…

机器学习 · 统计学 2018-07-10 Shengjia Zhao , Jiaming Song , Stefano Ermon

Lagrangian decomposition (LD) is a relaxation method that provides a dual bound for constrained optimization problems by decomposing them into more manageable sub-problems. This bound can be used in branch-and-bound algorithms to prune the…

人工智能 · 计算机科学 2024-08-26 Swann Bessa , Darius Dabert , Max Bourgeat , Louis-Martin Rousseau , Quentin Cappart

The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often…

机器学习 · 计算机科学 2024-08-09 Weidong Huang , Jiaming Ji , Chunhe Xia , Borong Zhang , Yaodong Yang

In safe Reinforcement Learning (RL), safety cost is typically defined as a function dependent on the immediate state and actions. In practice, safety constraints can often be non-Markovian due to the insufficient fidelity of state…

机器学习 · 计算机科学 2024-05-07 Siow Meng Low , Akshat Kumar

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-constrained RL methods like…

机器学习 · 计算机科学 2021-08-27 Baiyu Peng , Jingliang Duan , Jianyu Chen , Shengbo Eben Li , Genjin Xie , Congsheng Zhang , Yang Guan , Yao Mu , Enxin Sun

Safety is a primary challenge in real-world reinforcement learning (RL). Formulating safety requirements as state-wise constraints has become a prominent paradigm. Handling state-wise constraints with the Lagrangian method requires a…

机器学习 · 计算机科学 2026-05-04 Jiaming Zhang , Yujie Yang , Yao Lyu , Shengbo Eben Li , Liping Zhang

Primal-dual safe RL methods commonly perform iterations between the primal update of the policy and the dual update of the Lagrange Multiplier. Such a training paradigm is highly susceptible to the error in cumulative cost estimation since…

机器学习 · 计算机科学 2024-04-16 Zifan Wu , Bo Tang , Qian Lin , Chao Yu , Shangqin Mao , Qianlong Xie , Xingxing Wang , Dong Wang
‹ 上一页 1 2 3 10 下一页 ›