PAC-Bayes framework derives high-probability performance bounds for learned controllers on unknown stochastic linear discrete-time systems and provides efficient algorithms for finite and infinite controller spaces.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The paper gives sufficient conditions for Nash equilibrium existence in finite-population aggregative LQG games under delayed discrete mean-state observations and quantifies the extra cost relative to zero-latency and continuous-observation baselines.
citing papers explorer
-
A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems
PAC-Bayes framework derives high-probability performance bounds for learned controllers on unknown stochastic linear discrete-time systems and provides efficient algorithms for finite and infinite controller spaces.
-
Continuous Aggregative LQG Games with Delayed Discrete Observations
The paper gives sufficient conditions for Nash equilibrium existence in finite-population aggregative LQG games under delayed discrete mean-state observations and quantifies the extra cost relative to zero-latency and continuous-observation baselines.