Optimal Control of Point-to-Point Navigation in Turbulent Flows using Reinforcement Learning.
Michele BuzzicottiLuca BiferaleFabio BonaccorsoPatricio Clark Di LeoniKristian GustavssonPublished in: AIRO@AI*IA (2020)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- dynamic programming
- feedback control
- rl algorithms
- infinite horizon
- class of nonlinear systems
- control strategy
- actor critic
- control law
- risk sensitive
- function approximation
- optimal control problems
- brownian motion
- state space
- learning algorithm
- markov decision processes
- policy iteration
- reinforcement learning methods
- mathematical model
- lyapunov function
- average cost
- control scheme
- machine learning