English
Related papers

Related papers: Extreme Value Policy Optimization for Safe Reinfor…

200 papers

Extreme value theory provides rigorous theory and statistical tools for extrapolation in machine learning, particularly in settings where traditional methods struggle due to data scarcity in the tails. A broad range of tasks benefit from…

Machine Learning · Statistics 2026-05-05 Sebastian Engelke , Nicola Gnecco , Anne Sabourin

Recent advancements in Distributional Reinforcement Learning (DRL) for modeling loss distributions have shown promise in developing hedging strategies in derivatives markets. A common approach in DRL involves learning the quantiles of loss…

Risk Management · Quantitative Finance 2024-08-28 Parvin Malekzadeh , Zissis Poulos , Jacky Chen , Zeyu Wang , Konstantinos N. Plataniotis

We study the problem of training and fine-tuning expressive policies with online reinforcement learning (RL) given an offline dataset. Training expressive policy classes with online RL present a unique challenge of stable value…

Machine Learning · Computer Science 2026-05-01 Perry Dong , Qiyang Li , Dorsa Sadigh , Chelsea Finn

Machine learning is vital in high-stakes domains, yet conventional validation methods rely on averaging metrics like mean squared error (MSE) or mean absolute error (MAE), which fail to quantify extreme errors. Worst-case prediction…

Machine Learning · Computer Science 2025-04-01 Umberto Michelucci , Francesca Venturini

We study risk-sensitive Reinforcement Learning (RL), where we aim to maximize the Conditional Value at Risk (CVaR) with a fixed risk tolerance $\tau$. Prior theoretical work studying risk-sensitive RL focuses on the tabular Markov Decision…

Machine Learning · Computer Science 2023-11-21 Yulai Zhao , Wenhao Zhan , Xiaoyan Hu , Ho-fung Leung , Farzan Farnia , Wen Sun , Jason D. Lee

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied…

Machine Learning · Computer Science 2024-05-06 Zhongchang Sun , Sihong He , Fei Miao , Shaofeng Zou

Reinforcement learning for control over continuous spaces typically uses high-entropy stochastic policies, such as Gaussian distributions, for local exploration and estimating policy gradient to optimize performance. Many robotic control…

Machine Learning · Computer Science 2024-04-03 Ya-Chien Chang , Sicun Gao

In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or…

Machine Learning · Computer Science 2026-05-11 Dominik Wagner , Ankit Kanwar , Luke Ong

Although Reinforcement Learning (RL) algorithms have found tremendous success in simulated domains, they often cannot directly be applied to physical systems, especially in cases where there are hard constraints to satisfy (e.g. on safety…

Machine Learning · Computer Science 2020-08-28 Harsh Satija , Philip Amortila , Joelle Pineau

Ultra-reliable low-latency communications (URLLC) require innovative approaches to modeling channel and interference dynamics, extending beyond traditional average estimates to encompass entire statistical distributions, including rare and…

Systems and Control · Electrical Eng. & Systems 2025-01-22 Fateme Salehi , Aamir Mahmood , Sinem Coleri , Mikael Gidlund

Risk measures such as Conditional Value-at-Risk (CVaR) focus on extreme losses, where scarce tail data makes model error unavoidable. To hedge misspecification, one evaluates worst-case tail risk over an ambiguity set. Using Extreme Value…

Risk Management · Quantitative Finance 2026-01-22 Anand Deo

The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumulative discounted or long-run average cost/reward. In…

Machine Learning · Computer Science 2022-05-25 Prashanth L. A. , Michael Fu

Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency, or fine-tune smaller…

Artificial Intelligence · Computer Science 2026-04-02 Runda Guan , Xiangqing Shen , Jiajun Zhang , Yifan Zhang , Jian Cheng , Rui Xia

In recent years, Reinforcement Learning (RL) has been applied to real-world problems with increasing success. Such applications often require to put constraints on the agent's behavior. Existing algorithms for constrained RL (CRL) rely on…

Machine Learning · Computer Science 2023-03-07 Ted Moskovitz , Brendan O'Donoghue , Vivek Veeriah , Sebastian Flennerhag , Satinder Singh , Tom Zahavy

We consider the problem of evaluating risk for a system that is modeled by a complex stochastic simulation with many possible input parameter values. Two sources of computational burden can be identified: the effort associated with…

Methodology · Statistics 2024-03-29 Armin Khayyer , Alexander Vinel , Joseph J. Kennedy

Safe reinforcement learning aims to learn the optimal policy while satisfying safety constraints, which is essential in real-world applications. However, current algorithms still struggle for efficient policy updates with hard constraint…

Machine Learning · Computer Science 2022-06-20 Linrui Zhang , Li Shen , Long Yang , Shixiang Chen , Bo Yuan , Xueqian Wang , Dacheng Tao

Motivated by the prominence of Conditional Value-at-Risk (CVaR) as a measure for tail risk in settings affected by uncertainty, we develop a new formula for approximating CVaR based optimization objectives and their gradients from limited…

Methodology · Statistics 2020-08-25 Anand Deo , Karthyek Murthy

When safety is formulated as a limit of cumulative cost, safe reinforcement learning (RL) aims to learn policies that maximize return subject to the cost constraint in data collection and deployment. Off-policy safe RL methods, although…

Machine Learning · Computer Science 2026-03-26 Guopeng Li , Matthijs T. J. Spaan , Julian F. P. Kooij

Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance. In this paper, we formalize it with a constrained RL formulation in the distributional RL setting.…

Machine Learning · Computer Science 2021-03-01 Jianyi Zhang , Paul Weng

Constraint handling plays a key role in solving realistic complex optimization problems. Though intensively discussed in the last few decades, existing constraint handling techniques predominantly rely on human experts' designs, which more…

Neural and Evolutionary Computing · Computer Science 2026-02-03 Qianhao Zhu , Sijie Ma , Zeyuan Ma , Hongshu Guo , Yue-Jiao Gong