English
Related papers

Related papers: Safe Langevin Soft Actor Critic

200 papers

Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However,…

Machine Learning · Computer Science 2025-07-14 Tong Liu , Yinuo Wang , Xujie Song , Wenjun Zou , Liangfa Chen , Likun Wang , Bin Shuai , Jingliang Duan , Shengbo Eben Li

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

Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. Designing RL algorithms that optimize these objectives can be a costly and painstaking process. This paper presents…

Machine Learning · Computer Science 2023-04-26 Juan Jose Garau-Luis , Yingjie Miao , John D. Co-Reyes , Aaron Parisi , Jie Tan , Esteban Real , Aleksandra Faust

Conditional value-at-risk (CVaR) is a prominent risk measure in financial engineering, energy systems, and supply chain management. In these domains, Markov decision processes (MDPs) with a long-run CVaR criterion effectively mitigate cost…

Optimization and Control · Mathematics 2026-03-11 Qixin Wang , Hao Cao , Jian-Qiang Hu , Mingjie Hu , Li Xia

Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance: methods that tightly enforce safety often cripple task…

Machine Learning · Computer Science 2026-02-19 Daniel Bethell , Simos Gerasimou , Radu Calinescu , Calum Imrie

In this paper, we study the stochastic combinatorial multi-armed bandit problem under semi-bandit feedback. While much work has been done on algorithms that optimize the expected reward for linear as well as some general reward functions,…

Machine Learning · Computer Science 2021-12-03 Shaarad Ayyagari , Ambedkar Dukkipati

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

Off-policy actor-critic methods in reinforcement learning train a critic with temporal-difference updates and use it as a learning signal for the policy (actor). This design typically achieves higher sample efficiency than purely on-policy…

Machine Learning · Computer Science 2026-01-05 Uğurcan Özalp

Many reinforcement learning methods achieve great success in practice but lack theoretical foundation. In this paper, we study the convergence analysis on the problem of the Linear Quadratic Regulator (LQR). The global linear convergence…

Optimization and Control · Mathematics 2020-07-09 Zeyu Jin , Johann Michael Schmitt , Zaiwen Wen

To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a…

Machine Learning · Computer Science 2020-10-21 Yuguang Yue , Zhendong Wang , Mingyuan Zhou

Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in addition to maximizing a reward objective. Model-based RL algorithms hold promise for reducing unsafe real-world actions: they may synthesize policies…

Machine Learning · Computer Science 2021-12-16 Yecheng Jason Ma , Andrew Shen , Osbert Bastani , Dinesh Jayaraman

Text-based games are a popular testbed for language-based reinforcement learning (RL). In previous work, deep Q-learning is commonly used as the learning agent. Q-learning algorithms are challenging to apply to complex real-world domains…

Machine Learning · Computer Science 2023-06-28 Weichen Li , Rati Devidze , Sophie Fellenz

This work examines average-reward reinforcement learning with general policy parametrization. Existing state-of-the-art (SOTA) guarantees for this problem are either suboptimal or hindered by several challenges, including poor scalability…

Machine Learning · Computer Science 2025-05-07 Swetha Ganesh , Washim Uddin Mondal , Vaneet Aggarwal

Many sequential decision problems involve finding a policy that maximizes total reward while obeying safety constraints. Although much recent research has focused on the development of safe reinforcement learning (RL) algorithms that…

Machine Learning · Computer Science 2021-07-20 Nolan Wagener , Byron Boots , Ching-An Cheng

Constrained Reinforcement Learning (RL) has emerged as a significant research area within RL, where integrating constraints with rewards is crucial for enhancing safety and performance across diverse control tasks. In the context of heating…

Machine Learning · Computer Science 2024-10-01 Baohe Zhang , Lilli Frison , Thomas Brox , Joschka Bödecker

Conditional Value-at-Risk (CVaR) is a widely used risk metric in applications such as finance. We derive concentration bounds for CVaR estimates, considering separately the cases of light-tailed and heavy-tailed distributions. In the…

Machine Learning · Computer Science 2019-08-27 Prashanth L. A. , Krishna Jagannathan , Ravi Kumar Kolla

Expressive generative policies such as diffusion and flow models are appealing for MaxEnt online reinforcement learning because of their ability to model multimodal and highly non-Gaussian action distributions. However, training effective…

Machine Learning · Computer Science 2026-05-12 Ke He , Le He , Shunpu Tang , Yafei Wang , Lisheng Fan

Safety is an indispensable requirement for applying reinforcement learning (RL) to real problems. Although there has been a surge of safe RL algorithms proposed in recent years, most existing work typically 1) relies on receiving numeric…

Machine Learning · Computer Science 2024-01-12 Akifumi Wachi , Wataru Hashimoto , Kazumune Hashimoto

Safety in reinforcement learning has become increasingly important in recent years. Yet, existing solutions either fail to strictly avoid choosing unsafe actions, which may lead to catastrophic results in safety-critical systems, or fail to…

Machine Learning · Computer Science 2021-06-14 Sanae Amani , Christos Thrampoulidis , Lin F. Yang

Merging into the highway from the on-ramp is an essential scenario for automated driving. The decision-making under the scenario needs to balance the safety and efficiency performance to optimize a long-term objective, which is challenging…

Robotics · Computer Science 2021-03-09 Yiting Kong , Yang Guan , Jingliang Duan , Shengbo Eben Li , Qi Sun , Bingbing Nie