paper-with-me

Papers Safe Reinforcement Learning

“Safe Reinforcement Learning” 태그가 달린 논문 306편 · 필터 해제

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints

2025-06-09 · Yaswanth Chittepu, Blossom Metevier, Will Schwarzer, Austin Hoag 외

Existing approaches to language model alignment often treat safety as a tradeoff against helpfulness, which can lead to unacceptable responses in sensitive domains. To ensure reliable performance in such settings, we pro…

Safe Reinforcement Learning

Provably Safe Reinforcement Learning from Analytic Gradients

2025-06-02 · Tim Walter, Hannah Markgraf, Jonathan Külz, Matthias Althoff

Deploying autonomous robots in safety-critical applications requires safety guarantees. Provably safe reinforcement learning is an active field of research which aims to provide such guarantees using safeguards. These sa…

reinforcement-learningReinforcement LearningSafe Reinforcement Learning

A Provable Approach for End-to-End Safe Reinforcement Learning

2025-05-28 · Akifumi Wachi, Kohei Miyaguchi, Takumi Tanabe, Rei Sato 외

A longstanding goal in safe reinforcement learning (RL) is a method to ensure the safety of a policy throughout the entire process, from learning to operation. However, existing safe RL paradigms inherently struggle to a…

Gaussian ProcessesReinforcement Learning (RL)Safe Reinforcement Learning

Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies

2025-05-22 · Runze Yan, Xun Shen, Akifumi Wachi, Sebastien Gros 외

When applying offline reinforcement learning (RL) in healthcare scenarios, the out-of-distribution (OOD) issues pose significant risks, as inappropriate generalization beyond clinical expertise can result in potentially …

Offline RLQ-Learningreinforcement-learningReinforcement Learning+2

Risk-Aware Safe Reinforcement Learning for Control of Stochastic Linear Systems

2025-05-14 · Babak Esmaeili, Nariman Niknejad, Hamidreza Modares

This paper presents a risk-aware safe reinforcement learning (RL) control design for stochastic discrete-time linear systems. Rather than using a safety certifier to myopically intervene with the RL controller, a risk-in…

Reinforcement Learning (RL)Safe Reinforcement Learning

Feasibility-Aware Pessimistic Estimation: Toward Long-Horizon Safety in Offline RL

2025-05-13 · Zhikun Tao, Gang Xiong, He Fang, Zhen Shen 외

Offline safe reinforcement learning(OSRL) derives constraint-satisfying policies from pre-collected datasets, offers a promising avenue for deploying RL in safety-critical real-world domains such as robotics. However, th…

Offline RLSafe Reinforcement Learning

Skill-based Safe Reinforcement Learning with Risk Planning

2025-05-02 · Hanping Zhang, Yuhong Guo

Safe Reinforcement Learning (Safe RL) aims to ensure safety when an RL agent conducts learning by interacting with real-world environments where improper actions can induce high costs or lead to severe consequences. In t…

reinforcement-learningReinforcement LearningSafe Reinforcement Learning

Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation

2025-04-30 · Luca Marzari, Francesco Trotti, Enrico Marchesini, Alessandro Farinelli

Achieving safe autonomous navigation systems is critical for deploying robots in dynamic and uncertain real-world environments. In this paper, we propose a hierarchical control framework leveraging neural network verific…

Autonomous NavigationSafe Reinforcement Learning

Anytime Safe Reinforcement Learning

2025-04-23 · Pol Mestres, Arnau Marzabal, Jorge Cortés

This paper considers the problem of solving constrained reinforcement learning problems with anytime guarantees, meaning that the algorithmic solution returns a safe policy regardless of when it is terminated. Drawing in…

reinforcement-learningReinforcement LearningSafe Reinforcement Learning

TraCeS: Trajectory Based Credit Assignment From Sparse Safety Feedback

2025-04-17 · Siow Meng Low, Akshat Kumar

In safe reinforcement learning (RL), auxiliary safety costs are used to align the agent to safe decision making. In practice, safety constraints, including cost functions and budgets, are unknown or hard to specify, as i…

continuous-controlContinuous ControlDecision MakingReinforcement Learning (RL)+1

Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents

2025-04-04 · Jaymari Chua, Chen Wang, Lina Yao

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often …

Safe Reinforcement Learning

Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards

2025-04-03 · Hanping Zhang, Yuhong Guo

Safe Reinforcement Learning (Safe RL) aims to train an RL agent to maximize its performance in real-world environments while adhering to safety constraints, as exceeding safety violation limits can result in severe conse…

Safe Reinforcement Learning

Bresa: Bio-inspired Reflexive Safe Reinforcement Learning for Contact-Rich Robotic Tasks

2025-03-27 · Heng Zhang, Gokhan Solak, Arash Ajoudani

Ensuring safety in reinforcement learning (RL)-based robotic systems is a critical challenge, especially in contact-rich tasks within unstructured environments. While the state-of-the-art safe RL approaches mitigate risk…

Reinforcement Learning (RL)Safe ExplorationSafe Reinforcement Learning

Safe RLHF-V: Safe Reinforcement Learning from Human Feedback in Multimodal Large Language Models

2025-03-22 · Jiaming Ji, Xinyu Chen, Rui Pan, Han Zhu 외

Multimodal large language models (MLLMs) are critical for developing general-purpose AI assistants, yet they face growing safety risks. How can we ensure that MLLMs are safely aligned to prevent undesired behaviors such …

MisinformationSafe Reinforcement LearningSafety Alignment

Reachable Sets-based Trajectory Planning Combining Reinforcement Learning and iLQR

2025-03-19 · Wenjie Huang, Yang Li, Shijie Yuan, Jingjia Teng 외

The driving risk field is applicable to more complex driving scenarios, providing new approaches for safety decision-making and active vehicle control in intricate environments. However, existing research often overlooks…

reinforcement-learningReinforcement LearningSafe Reinforcement LearningTrajectory Planning

Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation

2025-03-15 · Jianqi Gao, Xizheng Pang, Qi Liu, YanJie Li

Reinforcement learning-based mapless navigation holds significant potential. However, it faces challenges in indoor environments with local minima area. This paper introduces a safe mapless navigation framework utilizing…

Hierarchical Reinforcement LearningMotion Planningreinforcement-learningReinforcement Learning+1

Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning

2025-03-13 · Duc Kien Doan, Bang Giang Le, Viet Cuong Ta

In safe reinforcement learning, agent needs to balance between exploration actions and safety constraints. Following this paradigm, domain transfer approaches learn a prior Q-function from the related environments to pre…

Contrastive LearningRepresentation LearningSafe Reinforcement Learning

HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents

2025-03-11 · Tristan Tomilin, Meng Fang, Mykola Pechenizkiy

Advancing safe autonomous systems through reinforcement learning (RL) requires robust benchmarks to evaluate performance, analyze methods, and assess agent competencies. Humans primarily rely on embodied visual perceptio…

NavigateReinforcement Learning (RL)Safe Reinforcement Learning

Probabilistic Shielding for Safe Reinforcement Learning

2025-03-09 · Edwin Hamel-De le Court, Francesco Belardinelli, Alexander W. Goodall

In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attention in recent years has been given to Saf…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

2025-03-05 · Borong Zhang, Yuhao Zhang, Jiaming Ji, Yingshan Lei 외

Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robo…

Safe Reinforcement LearningSafety AlignmentVision-Language-Action
1–20 / 306 다음 →