Copertina

Uniformly Safe RL with Objective Suppression for Multi-Constraint Safety-Critical Applications

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Zihan, Booher, Jonathan, Rohanimanesh, Khashayar, Liu, Wei, Petiushko, Aleksandr, Garg, Animesh
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving
di: Booher, Jonathan, et al.
Pubblicazione: (2024)

SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
di: Zhang, Jiawei, et al.
Pubblicazione: (2025)

ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
di: Zhou, Zihan, et al.
Pubblicazione: (2025)

Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation
di: Georgiev, Ignat, et al.
Pubblicazione: (2024)

Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints
di: Low, Siow Meng, et al.
Pubblicazione: (2024)

Probabilistic Constraint for Safety-Critical Reinforcement Learning
di: Chen, Weiqin, et al.
Pubblicazione: (2023)

Cooperative Multi-agent RL with Communication Constraints
di: Xiong, Nuoya, et al.
Pubblicazione: (2026)

PWM: Policy Learning with Multi-Task World Models
di: Georgiev, Ignat, et al.
Pubblicazione: (2024)

SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation
di: Zhou, Zihan, et al.
Pubblicazione: (2024)

Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
di: Gu, Shangding, et al.
Pubblicazione: (2024)

Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL
di: Kim, Sung-Hyun, et al.
Pubblicazione: (2025)

A Safety Modulator Actor-Critic Method in Model-Free Safe Reinforcement Learning and Application in UAV Hovering
di: Qi, Qihan, et al.
Pubblicazione: (2024)

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
di: Pavlenko, Kirill, et al.
Pubblicazione: (2026)

Training RL Agents for Multi-Objective Network Defense Tasks
di: Molina-Markham, Andres, et al.
Pubblicazione: (2025)

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?
di: Chen, Zihan, et al.
Pubblicazione: (2025)

FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning
di: Zhang, Xikai, et al.
Pubblicazione: (2026)

Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare
di: Fang, Nan, et al.
Pubblicazione: (2024)

Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles
di: Zhang, Xinglong, et al.
Pubblicazione: (2021)

SafeCoT: Improving VLM Safety with Minimal Reasoning
di: Ma, Jiachen, et al.
Pubblicazione: (2025)

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content
di: Stepanov, Ihor, et al.
Pubblicazione: (2026)

DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems
di: Yoo, Se-Wook, et al.
Pubblicazione: (2025)

AviaSafe: A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecasts
di: Zhu, Zijian, et al.
Pubblicazione: (2026)

Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning
di: Chemingui, Yassine, et al.
Pubblicazione: (2024)

Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS
di: Jin, Can, et al.
Pubblicazione: (2025)

GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL
di: Liu, Zifan, et al.
Pubblicazione: (2026)

Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual
di: Li, Yining, et al.
Pubblicazione: (2026)

Multi-Objective Constraint Inference using Inverse reinforcement learning
di: Shah, Syed Ihtesham Hussain, et al.
Pubblicazione: (2026)

Reinforcement Learning with $ω$-Regular Objectives and Constraints
di: Wagner, Dominik, et al.
Pubblicazione: (2025)

Robust Evolutionary Multi-Objective Network Architecture Search for Reinforcement Learning (EMNAS-RL)
di: Adde, Nihal Acharya, et al.
Pubblicazione: (2025)

SafeSeek: Universal Attribution of Safety Circuits in Language Models
di: Yu, Miao, et al.
Pubblicazione: (2026)

Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
di: Yao, Yihang, et al.
Pubblicazione: (2023)

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
di: Ji, Jiaming, et al.
Pubblicazione: (2023)

Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
di: Cherepanov, Egor, et al.
Pubblicazione: (2024)

COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability
di: Ding, Yizhuo, et al.
Pubblicazione: (2025)

ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems
di: Cherepanov, Egor, et al.
Pubblicazione: (2025)

Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives
di: Xiong, Wei, et al.
Pubblicazione: (2025)

A Survey of Constraint Formulations in Safe Reinforcement Learning
di: Wachi, Akifumi, et al.
Pubblicazione: (2024)

Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care
di: Shirali, Ali, et al.
Pubblicazione: (2023)

MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility Applications
di: Algazinov, Aleksandr, et al.
Pubblicazione: (2025)

CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building
di: Byrnes, Walker, et al.
Pubblicazione: (2024)