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