Robuta

https://openreview.net/forum?id=97QXO0uBEO Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning | OpenReview Safety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots. While most approaches in the Safe... safe reinforcement learninglong termhandlingsafety https://openreview.net/forum?id=kZFKwApeQO GUARD: A Safe Reinforcement Learning Benchmark | OpenReview Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving,... safe reinforcement learningguardbenchmarkopenreview https://openreview.net/forum?id=mcN0ezbnzO Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking | OpenReview Ensuring the safety of reinforcement learning (RL) algorithms is crucial to unlock their potential for many real-world tasks. However, vanilla RL and most safe... safe reinforcement learningconceptual analysissurveybenchmarkingopenreview https://openreview.net/forum?id=hZztyfmr8n&referrer=%5Bthe%20profile%20of%20Yue%20Deng%5D(%2Fprofile%3Fid%3D~Yue_Deng4) COSTAR: Dynamic Safety Constraints Adaptation in Safe Reinforcement Learning | OpenReview Recent advancements in safe reinforcement learning (safe RL) have focused on developing agents that maximize rewards while satisfying predefined safety... safe reinforcement learningsafety constraintscostardynamicadaptation https://openreview.net/forum?id=e85xf2d17F Online Optimization for Offline Safe Reinforcement Learning | OpenReview We study the problem of Offline Safe Reinforcement Learning (OSRL), where the goal is to learn a reward-maximizing policy from fixed data under a cumulative... safe reinforcement learningonline optimizationofflineopenreview https://openreview.net/forum?id=ZHVO9IeHJDg Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning | OpenReview We propose a safe model-based reinforcement learning algorithm incorporating conservative and adaptive penalty. safe reinforcement learningconservativeadaptivepenalty https://www.pnnl.gov/publications/safe-reinforcement-learning-emergency-load-shedding-power-systems Safe Reinforcement Learning for Emergency Load Shedding of Power Systems | Conference Paper | PNNL safe reinforcement learning https://arxiv.org/abs/2511.12417 [2511.12417] Integrating Neural Differential Forecasting with Safe Reinforcement Learning for Blood... Abstract page for arXiv paper 2511.12417: Integrating Neural Differential Forecasting with Safe Reinforcement Learning for Blood Glucose Regulation safe reinforcement learning https://openreview.net/forum?id=cgSXpAR4Gl Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees |... Robustness and safety are critical for the trustworthy deployment of deep reinforcement learning. Real-world decision making applications require algorithms... safe reinforcement learningoptimal transportperturbationsrobustnessguarantees https://openreview.net/forum?id=tsE5HLYtYg SafeDreamer: Safe Reinforcement Learning with World Models | OpenReview The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement... safe reinforcement learningworld modelsopenreview https://deepai.org/publication/safe-reinforcement-learning-using-robust-action-governor Safe Reinforcement Learning Using Robust Action Governor | DeepAI Feb 21, 2021 - 02/21/21 - Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the explora... safe reinforcement learningusingrobustactiongovernor https://openreview.net/forum?id=3uDEmsf3Jf OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning | OpenReview Offline safe reinforcement learning (RL) aims to train a policy that satisfies con- straints using a pre-collected dataset. Most current methods struggle with... safe reinforcement learningconditional distributionoasisshapingoffline