A framework for safe online exploration of nonlinear processes uses Gaussian process learning of residuals combined with Lyapunov-derived probabilistic control-invariant sets to guarantee high-probability stability while maximizing information gain.
Enhancing reinforcement learning robustness via integrated multiple-model adaptive control.IF AC-PapersOnLine, 58(14):360–366
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Safe Exploration for Nonlinear Processes Using Online Gaussian Process Learning
A framework for safe online exploration of nonlinear processes uses Gaussian process learning of residuals combined with Lyapunov-derived probabilistic control-invariant sets to guarantee high-probability stability while maximizing information gain.