[HTML][HTML] Safety constraint-guided reinforcement learning with linear temporal logic

R Kwon, G Kwon - Systems, 2023 - mdpi.com
In the context of reinforcement learning (RL), ensuring both safety and performance is
crucial, especially in real-world scenarios where mistakes can lead to severe …

Verification using formalised mathematics and theorem proving of reinforcement and deep learning

M Chevallier - 2024 - era.ed.ac.uk
In modern artificial intelligence research, frequently there is little emphasis on mathe-matical
certainty; results are often shown by experimentation, and understanding pre-cisely why a …

Joint Learning of Unknown Safety Constraints and Control Policies in Reinforcement Learning

LA Yifru - 2024 - search.proquest.com
Reinforcement learning (RL) has revolutionized decision-making across a wide range of
domains over the past few decades. Yet, deploying RL policies in real-world scenarios …