Safe rlhf: Safe reinforcement learning from human feedback
With the development of large language models (LLMs), striking a balance between the
performance and safety of AI systems has never been more critical. However, the inherent …
performance and safety of AI systems has never been more critical. However, the inherent …
Is sora a world simulator? a comprehensive survey on general world models and beyond
General world models represent a crucial pathway toward achieving Artificial General
Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual …
Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual …
Games for Artificial Intelligence Research: A Review and Perspectives
Games have been the perfect test-beds for artificial intelligence research for the
characteristics that widely exist in real-world scenarios. Learning and optimisation, decision …
characteristics that widely exist in real-world scenarios. Learning and optimisation, decision …
PKU-SafeRLHF: A Safety Alignment Preference Dataset for Llama Family Models
In this work, we introduce the PKU-SafeRLHF dataset, designed to promote research on
safety alignment in large language models (LLMs). As a sibling project to SafeRLHF and …
safety alignment in large language models (LLMs). As a sibling project to SafeRLHF and …
Deep Policy Optimization with Temporal Logic Constraints
Temporal logics, such as linear temporal logic (LTL), offer a precise means of specifying
tasks for (deep) reinforcement learning (RL) agents. In our work, we consider the setting …
tasks for (deep) reinforcement learning (RL) agents. In our work, we consider the setting …
Energy Management for Hybrid Electric Vehicles Using Safe Hybrid-Action Reinforcement Learning
Reinforcement learning has shown success in solving complex control problems, yet safety
remains paramount in engineering applications like energy management systems (EMS) …
remains paramount in engineering applications like energy management systems (EMS) …
Collaborative promotion: Achieving safety and task performance by integrating imitation reinforcement learning
C Zhang, X Zhang, H Zhang, F Zhu - Expert Systems with Applications, 2024 - Elsevier
Although the importance of safety is self-evident for artificial intelligence, like the two sides of
a coin, excessively focus on safety performance without considering task performance may …
a coin, excessively focus on safety performance without considering task performance may …
Feasibility Consistent Representation Learning for Safe Reinforcement Learning
In the field of safe reinforcement learning (RL), finding a balance between satisfying safety
constraints and optimizing reward performance presents a significant challenge. A key …
constraints and optimizing reward performance presents a significant challenge. A key …
Safe Multi-agent Reinforcement Learning with Natural Language Constraints
The role of natural language constraints in Safe Multi-agent Reinforcement Learning
(MARL) is crucial, yet often overlooked. While Safe MARL has vast potential, especially in …
(MARL) is crucial, yet often overlooked. While Safe MARL has vast potential, especially in …
Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding
Empowering safe exploration of reinforcement learning (RL) agents during training is a
critical impediment towards deploying RL agents in many real-world scenarios. Training RL …
critical impediment towards deploying RL agents in many real-world scenarios. Training RL …