A new online algorithm for adversarial linear control achieves square-root regret against steady-states attainable under affine controllers rather than constant inputs.
Responding to Promises: No- regret learning against followers with memory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Steady-state Based Approach to Online Non-stochastic Control
A new online algorithm for adversarial linear control achieves square-root regret against steady-states attainable under affine controllers rather than constant inputs.