A Behavioral Input-Output Parametrization of Control Policies with Suboptimality Guarantees.
Luca FurieriBaiwei GuoAndrea MartinGiancarlo Ferrari-TrecatePublished in: CoRR (2021)
Keyphrases
- input output
- control policies
- optimal policy
- control policy
- reinforcement learning
- control strategies
- control system
- internal states
- finite horizon
- noise cancellation
- motion control
- action space
- fuzzy controller
- ibm zenterprise
- machine learning
- data envelopment analysis
- reward function
- long run
- decision problems
- markov decision processes