2v2 Air Combat Confrontation Strategy Based on Reinforcement Learning

Safe Autonomous Driving with Latent Dynamics and State-Wise Constraints

“…The barrier function serves as a formal safety certificate associated with a control policy, guaranteeing the state-wise safety of a dynamical system [21,22]. Classical control theory often relaxes the stringent conditions of the barrier function into optimization formulations like linear programs [23,24] and quadratic programs [25,26].…”

“…Recent research has explored the joint learning of control policies and neural barrier functions to optimize state-wise safety constraints in reinforcement learning [27][28][29]. In the context of autonomous driving, ShieldNN [30] leverages CBF to design a safety filter neural network, providing safety assurances for environments with known bicycle dynamics models.…”

Towards a Deep Reinforcement Learning Model of Master Bay Stowage Planning

“…Various deep learning methods have addressed constraint learning through techniques such as backpropagation over (in)equality completions [27], differentiable projection layers that map interior points to boundary regions [43], convex programming layers [1], and problem-specific repair mechanisms [22]. In addition, safe reinforcement learning has approached feasibility through constrained MDPs with primal-dual techniques [26], soft barrier functions [79], and safety shields [3].…”