Bounds for the regret loss in dynamic programming under adaptive control.
Michael KolonkoPublished in: Z. Oper. Research (1983)
Keyphrases
- adaptive control
- dynamic programming
- regret bounds
- confidence bounds
- lower bound
- loss bounds
- expert advice
- worst case bounds
- reinforcement learning
- worst case
- nonlinear systems
- control method
- feedback control
- online learning
- upper bound
- control law
- linear regression
- optimal control
- adaptive controller
- state space
- dynamic environments
- expected loss
- control algorithm
- variable structure
- optimal policy
- bregman divergences
- autonomous control
- markov decision processes
- loss function
- fuzzy control
- data mining
- machine learning