-
Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement...
The dataset used in this paper is a comprehensive case study dataset, including Safe Navigation-Circle, Safe Navigation-Goal, and Safe Velocity-Half Cheetah environments. -
Safe RL policy synthesis in environments with unknown safety constraints
The dataset used in this paper is a small initial labeled dataset, safe trajectories Ds and unsafe trajectories Dus, and a pSTL safety specification template.
