A survey of safety and trustworthiness of large language models through the lens of verification and validation
Large language models (LLMs) have exploded a new heatwave of AI for their ability to
engage end-users in human-level conversations with detailed and articulate answers across …
engage end-users in human-level conversations with detailed and articulate answers across …
Safe reinforcement learning for power system control: A review
The large-scale integration of intermittent renewable energy resources introduces increased
uncertainty and volatility to the supply side of power systems, thereby complicating system …
uncertainty and volatility to the supply side of power systems, thereby complicating system …
[HTML][HTML] Machine learning meets advanced robotic manipulation
Automated industries lead to high quality production, lower manufacturing cost and better
utilization of human resources. Robotic manipulator arms have major role in the automation …
utilization of human resources. Robotic manipulator arms have major role in the automation …
Safe Multiagent Learning With Soft Constrained Policy Optimization in Real Robot Control
Due to a lack of safety considerations, a wide range of multiagent reinforcement learning
(MARL) applications are limited in real-world environments. Thus, ensuring MARL safety is …
(MARL) applications are limited in real-world environments. Thus, ensuring MARL safety is …
Balance reward and safety optimization for safe reinforcement learning: A perspective of gradient manipulation
Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world
applications. Nevertheless, managing the trade-off between reward and safety during …
applications. Nevertheless, managing the trade-off between reward and safety during …
Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Case Study
S Gu - arXiv preprint arXiv:2401.06603, 2024 - arxiv.org
Large Language Models (LLMs) have demonstrated remarkable capabilities for
reinforcement learning (RL) models, such as planning and reasoning capabilities. However …
reinforcement learning (RL) models, such as planning and reasoning capabilities. However …
ROSCOM: Robust Safe Reinforcement Learning on Stochastic Constraint Manifolds
Reinforcement Learning (RL) has demonstrated remarkable success across various
domains. Nonetheless, a significant challenge in RL is to ensure safety, particularly when …
domains. Nonetheless, a significant challenge in RL is to ensure safety, particularly when …
Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving
Z Zheng, S Gu - arXiv preprint arXiv:2405.18209, 2024 - arxiv.org
Ensuring safety in MARL, particularly when deploying it in real-world applications such as
autonomous driving, emerges as a critical challenge. To address this challenge, traditional …
autonomous driving, emerges as a critical challenge. To address this challenge, traditional …
SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimization
J Mhamed, S Gu - arXiv preprint arXiv:2311.00880, 2023 - arxiv.org
Incorporating safety is an essential prerequisite for broadening the practical applications of
reinforcement learning in real-world scenarios. To tackle this challenge, Constrained Markov …
reinforcement learning in real-world scenarios. To tackle this challenge, Constrained Markov …
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
In numerous reinforcement learning (RL) problems involving safety-critical systems, a key
challenge lies in balancing multiple objectives while simultaneously meeting all stringent …
challenge lies in balancing multiple objectives while simultaneously meeting all stringent …