From inverse optimal control to inverse reinforcement learning: A historical review.
Nematollah Ab AzarAref ShahmansoorianMohsen DavoudiPublished in: Annu. Rev. Control. (2020)
Keyphrases
- optimal control
- inverse reinforcement learning
- partially observable environments
- dynamic programming
- preference elicitation
- reinforcement learning
- control strategy
- infinite horizon
- reward function
- neural network
- temporal difference
- average cost
- optimal control problems
- control system
- cost function
- sufficient conditions