A two-player game representation for a class of infinite horizon control problems under state constraints.
Vincenzo BascoPeter M. DowerPublished in: ACC (2020)
Keyphrases
- control problems
- optimal control
- infinite horizon
- dynamic programming
- state space
- reinforcement learning
- partially observable
- finite horizon
- optimal policy
- markov decision processes
- markov decision process
- control strategy
- adaptive control
- machine learning
- real time
- policy iteration
- two player games
- control law
- mobile robot
- data mining