English
Related papers

Related papers: Provably Efficient CVaR RL in Low-rank MDPs

200 papers

Mainstream approximate action-value iteration reinforcement learning (RL) algorithms suffer from overestimation bias, leading to suboptimal policies in high-variance stochastic environments. Quantile-based action-value iteration methods…

Machine Learning · Computer Science 2025-12-09 Clinton Enwerem , Aniruddh G. Puranic , John S. Baras , Calin Belta

In high-stakes machine learning applications, it is crucial to not only perform well on average, but also when restricted to difficult examples. To address this, we consider the problem of training models in a risk-averse manner. We propose…

Machine Learning · Computer Science 2020-11-09 Sebastian Curi , Kfir. Y. Levy , Stefanie Jegelka , Andreas Krause

Robust reinforcement learning (Robust RL) seeks to handle epistemic uncertainty in environment dynamics, but existing approaches often rely on nested min--max optimization, which is computationally expensive and yields overly conservative…

Machine Learning · Computer Science 2025-10-15 Chenliang Li , Junyu Leng , Jiaxiang Li , Youbang Sun , Shixiang Chen , Shahin Shahrampour , Alfredo Garcia

We study model-based reinforcement learning (RL) for episodic Markov decision processes (MDP) whose transition probability is parametrized by an unknown transition core with features of state and action. Despite much recent progress in…

Machine Learning · Statistics 2024-11-19 Taehyun Hwang , Min-hwan Oh

In the classical Reinforcement Learning (RL) setting, one aims to find a policy that maximizes its expected return. This objective may be inappropriate in safety-critical domains such as healthcare or autonomous driving, where intrinsic…

Machine Learning · Computer Science 2022-05-19 M. Godbout , M. Heuillet , S. Chandra , R. Bhati , A. Durand

We study a first-order primal-dual subgradient method to optimize risk-constrained risk-penalized optimization problems, where risk is modeled via the popular conditional value at risk (CVaR) measure. The algorithm processes independent and…

Optimization and Control · Mathematics 2021-09-03 Avinash N. Madavan , Subhonmesh Bose

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve over time but their…

Machine Learning · Computer Science 2024-04-16 Huozhi Zhou , Jinglin Chen , Lav R. Varshney , Ashish Jagmohan

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli

In reward-free reinforcement learning (RL), an agent explores the environment first without any reward information, in order to achieve certain learning goals afterwards for any given reward. In this paper we focus on reward-free RL under…

Machine Learning · Computer Science 2023-03-21 Yuan Cheng , Ruiquan Huang , Jing Yang , Yingbin Liang

As representation learning becomes a powerful technique to reduce sample complexity in reinforcement learning (RL) in practice, theoretical understanding of its advantage is still limited. In this paper, we theoretically characterize the…

Machine Learning · Computer Science 2022-06-14 Yuan Cheng , Songtao Feng , Jing Yang , Hong Zhang , Yingbin Liang

Risk-sensitive reinforcement learning (RL) has garnered significant attention in recent years due to the growing interest in deploying RL agents in real-world scenarios. A critical aspect of risk awareness involves modeling highly rare risk…

Machine Learning · Computer Science 2023-08-30 Karthik Somayaji NS , Yu Wang , Malachi Schram , Jan Drgona , Mahantesh Halappanavar , Frank Liu , Peng Li

This paper presents a model-free reinforcement learning (RL) algorithm to solve the risk-averse optimal control (RAOC) problem for discrete-time nonlinear systems. While successful RL algorithms have been presented to learn optimal control…

Systems and Control · Electrical Eng. & Systems 2021-03-29 Yuzhen Han , Majid Mazouchi , Subramanya Nageshrao , Hamidreza Modares

Distributionally robust offline reinforcement learning (RL) aims to find a policy that performs the best under the worst environment within an uncertainty set using an offline dataset collected from a nominal model. While recent advances in…

Machine Learning · Computer Science 2025-01-07 Ruiquan Huang , Yingbin Liang , Jing Yang

Traditional reinforcement learning (RL) aims to maximize the expected total reward, while the risk of uncertain outcomes needs to be controlled to ensure reliable performance in a risk-averse setting. In this paper, we consider the problem…

Machine Learning · Computer Science 2023-01-18 Xian Yu , Siqian Shen

In dynamic programming (DP) and reinforcement learning (RL), an agent learns to act optimally in terms of expected long-term return by sequentially interacting with its environment modeled by a Markov decision process (MDP). More generally…

Machine Learning · Computer Science 2022-01-03 Mastane Achab , Gergely Neu

We propose and analyze algorithms for distributionally robust optimization of convex losses with conditional value at risk (CVaR) and $\chi^2$ divergence uncertainty sets. We prove that our algorithms require a number of gradient…

Optimization and Control · Mathematics 2020-12-14 Daniel Levy , Yair Carmon , John C. Duchi , Aaron Sidford

Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of…

Machine Learning · Computer Science 2019-08-09 Chi Jin , Zhuoran Yang , Zhaoran Wang , Michael I. Jordan

Conditional Value at Risk (CVaR) is widely used to account for the preferences of a risk-averse agent in the extreme loss scenarios. To study the effectiveness of randomization in interdiction games with an interdictor that is both risk and…

Computer Science and Game Theory · Computer Science 2020-03-19 Utsav Sadana , Erick Delage

Safe navigation for mobile robots demands policies that remain reliable under the high-consequence perception uncertainty of cluttered environments. Yet most existing safe reinforcement learning (RL) methods assess safety through average…

Robotics · Computer Science 2026-05-15 Qisong He , Xinmiao Huang , Jinwei Hu , Zhuoyun Li , Yi Dong , Changshun Wu , Xiaowei Huang

This paper develops a safety analysis method for stochastic systems that is sensitive to the possibility and severity of rare harmful outcomes. We define risk-sensitive safe sets as sub-level sets of the solution to a non-standard optimal…

Systems and Control · Electrical Eng. & Systems 2022-06-28 Margaret P. Chapman , Riccardo Bonalli , Kevin M. Smith , Insoon Yang , Marco Pavone , Claire J. Tomlin