English
Related papers

Related papers: A Simple Mixture Policy Parameterization for Impro…

200 papers

Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy…

Computation and Language · Computer Science 2026-05-26 Guochao Jiang , Jingyi Song , Guofeng Quan , Chuzhan Hao , Guohua Liu , Yuewei Zhang

We present the conditional value-at-risk (CVaR) in the context of Markov chains and Markov decision processes with reachability and mean-payoff objectives. CVaR quantifies risk by means of the expectation of the worst p-quantile. As such it…

Logic in Computer Science · Computer Science 2018-05-09 Jan Křetínský , Tobias Meggendorfer

Many of the challenges facing today's reinforcement learning (RL) algorithms, such as robustness, generalization, transfer, and computational efficiency are closely related to compression. Prior work has convincingly argued why minimizing…

Machine Learning · Computer Science 2021-09-08 Benjamin Eysenbach , Ruslan Salakhutdinov , Sergey Levine

Score-based methods are powerful across machine learning, but they face a paradox: theoretically path-independent, yet practically path-dependent. We resolve this by proving that practical training objectives differ from the ideal,…

Machine Learning · Computer Science 2026-05-12 Wei Chen , Jiacheng Li , Shigui Li , Zhiqi Lin , Junmei Yang , John Paisley , Delu Zeng

Risk-averse decision-making under uncertainty in partially observable domains is a central challenge in artificial intelligence and is essential for developing reliable autonomous agents. The formal framework for such problems is the…

Statistics Theory · Mathematics 2026-02-27 Yaacov Pariente , Vadim Indelman

We consider continuous-time stochastic optimal control problems featuring Conditional Value-at-Risk (CVaR) in the objective. The major difficulty in these problems arises from time-inconsistency, which prevents us from directly using…

Optimization and Control · Mathematics 2020-05-27 Christopher W. Miller , Insoon Yang

Data in the real-world classification problems are always imbalanced or long-tailed, wherein the majority classes have the most of the samples that dominate the model training. In such setting, the naive model tends to have poor performance…

Machine Learning · Computer Science 2023-08-30 Hong Zhu , Runpeng Yu , Xing Tang , Yifei Wang , Yuan Fang , Yisen Wang

Excellent tail performance is crucial for modern machine learning tasks, such as algorithmic fairness, class imbalance, and risk-sensitive decision making, as it ensures the effective handling of challenging samples within a dataset. Tail…

Information Retrieval · Computer Science 2024-02-29 Riku Togashi , Tatsushi Oka , Naoto Ohsaka , Tetsuro Morimura

This paper examines reinforcement learning (RL) in infinite-horizon decision processes with almost-sure safety constraints, crucial for applications like autonomous systems, finance, and resource management. We propose a doubly-regularized…

Machine Learning · Computer Science 2025-09-17 Pekka Malo , Lauri Viitasaari , Antti Suominen , Eeva Vilkkumaa , Olli Tahvonen

We investigate the challenge of parametrizing policies for reinforcement learning (RL) in high-dimensional continuous action spaces. Our objective is to develop a multimodal policy that overcomes limitations inherent in the commonly-used…

Machine Learning · Computer Science 2023-07-21 Zhiao Huang , Litian Liang , Zhan Ling , Xuanlin Li , Chuang Gan , Hao Su

Constrained Reinforcement Learning (CRL) addresses sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints. In this setting, policy-based…

Machine Learning · Computer Science 2025-06-09 Alessandro Montenegro , Leonardo Cesani , Marco Mussi , Matteo Papini , Alberto Maria Metelli

We consider the problem of finding a policy that maximizes an expected reward throughout the trajectory of an agent that interacts with an unknown environment. Frequently denoted Reinforcement Learning, this framework suffers from the need…

Systems and Control · Electrical Eng. & Systems 2020-09-30 Juan Cervino , Harshat Kumar , Alejandro Ribeiro

Recent advances in large language models (LLMs) have shown that reasoning ability can be significantly enhanced through Reinforcement Learning with Verifiable Rewards (RLVR). Group Relative Policy Optimization (GRPO) has emerged as the de…

Computation and Language · Computer Science 2025-10-13 Jingyu Zhou , Lu Ma , Hao Liang , Chengyu Shen , Bin Cui , Wentao Zhang

Optimization problems characterized by both discrete and continuous variables are common across various disciplines, presenting unique challenges due to their complex solution landscapes and the difficulty of navigating mixed-variable…

Optimization and Control · Mathematics 2024-06-03 Haoyan Zhai , Qianli Hu , Jiangning Chen

Experience replay is a core ingredient of modern deep reinforcement learning, yet its benefits in policy optimization are poorly understood beyond empirical heuristics. This paper develops a novel theoretical framework for experience replay…

Machine Learning · Computer Science 2026-02-04 Hua Zheng , Wei Xie , M. Ben Feng

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

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function space, as opposed to…

Machine Learning · Computer Science 2023-01-26 Naman Agarwal , Brian Bullins , Karan Singh

We study reinforcement learning (RL) in the agnostic policy learning setting, where the goal is to find a policy whose performance is competitive with the best policy in a given class of interest $\Pi$ -- crucially, without assuming that…

Machine Learning · Computer Science 2025-07-08 Uri Sherman , Tomer Koren , Yishay Mansour

Reinforcement learning with verifiable rewards (RLVR) has become a core post-training recipe. Introducing suitable off-policy trajectories into on-policy exploration accelerates RLVR convergence and raises the performance ceiling, yet…

Machine Learning · Computer Science 2026-04-23 Chuanyu Qin , Chenxu Yang , Qingyi Si , Naibin Gu , Dingyu Yao , Zheng Lin , Peng Fu , Nan Duan , Jiaqi Wang

We study a discrete-time multi-period portfolio optimization problem under an explicit constraint on the Deviation Conditional Value-at-Risk (DCVaR), defined as the excess of Conditional Value-at-Risk over expected terminal wealth. The…

Portfolio Management · Quantitative Finance 2026-04-17 Jérôme Lelong , Véronique Maume-Deschamps , William Thevenot