Optimal Control of Point-to-Point Navigation in Turbulent Time Dependent Flows Using Reinforcement Learning.
Michele BuzzicottiLuca BiferaleFabio BonaccorsoPatricio Clark Di LeoniKristian GustavssonPublished in: AI*IA (2020)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- dynamic programming
- rl algorithms
- feedback control
- class of nonlinear systems
- risk sensitive
- optimal control problems
- infinite horizon
- control strategy
- brownian motion
- reinforcement learning algorithms
- control law
- model free
- state space
- actor critic
- markov decision processes
- learning algorithm
- queueing systems
- continuous stirred tank reactor
- average cost
- action selection
- control method
- optimal policy