RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
113870–113900
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
DSGNAR optimization framework for PINNs reaches relative L2 errors of 3e-16 in double precision and improves prior results by 5-8 orders of magnitude on Burgers' and high-dimensional Poisson problems while remaining faster.
Introduces natural-gradient versions of Heavy-Ball and Nesterov momentum methods for function approximation on differentiable nonlinear manifolds.
citing papers explorer
-
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
-
An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks
DSGNAR optimization framework for PINNs reaches relative L2 errors of 3e-16 in double precision and improves prior results by 5-8 orders of magnitude on Burgers' and high-dimensional Poisson problems while remaining faster.
-
Natural gradient descent with momentum
Introduces natural-gradient versions of Heavy-Ball and Nesterov momentum methods for function approximation on differentiable nonlinear manifolds.