ebpc-9
–Neural Information Processing Systems
Linear Quadratic Regulator (LQR) and Linear Quadratic Gaussian (LQG) control are foundational and extensively researched problems in optimal control. We investigate LQR and LQG problems with semi-adversarial perturbations and timevarying adversarial bandit loss functions. The best-known sublinear regret algorithm of Gradu et al. [2020] has a T
Neural Information Processing Systems
Mar-22-2025, 09:44:13 GMT