Optimal dynamic Control Allocation with guaranteed constraints and online Reinforcement Learning.
Patrik KolaricVictor G. LopezFrank L. LewisPublished in: Autom. (2020)
Keyphrases
- reinforcement learning
- optimal control
- control policy
- control problems
- dynamic programming
- online learning
- robot control
- dynamic environments
- dynamic constraints
- optimal allocation
- real time
- markov decision processes
- function approximation
- control strategy
- optimality criteria
- optimal solution
- dynamic allocation
- constraint satisfaction
- state space
- control policies
- long run
- linear constraints
- control strategies
- control method
- learning process
- adaptive control
- batch mode
- infinite horizon
- multi agent reinforcement learning
- optimal policy
- objective function
- capacity allocation