Optimal control of point-to-point navigation in turbulent time-dependent flows using Reinforcement Learning.
Michele BuzzicottiLuca BiferaleFabio BonaccorsoPatricio Clark Di LeoniKristian GustavssonPublished in: CoRR (2021)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- dynamic programming
- feedback control
- class of nonlinear systems
- optimal control problems
- actor critic
- state space
- function approximation
- risk sensitive
- brownian motion
- learning algorithm
- reinforcement learning algorithms
- control law
- rl algorithms
- control strategy
- infinite horizon
- travel time
- optimal policy
- machine learning
- adaptive control
- finite state
- lyapunov function
- policy gradient
- linear quadratic
- mobile robot