Robust Control in the Worst Case Using Continuous Time Reinforcement Learning.
Adolfo PerrusquíaWen YuXiaoou LiPublished in: SMC (2020)
Keyphrases
- optimal control
- reinforcement learning
- worst case
- control problems
- upper bound
- state space
- robot control
- lower bound
- control system
- dynamic programming
- control strategy
- control policy
- computationally efficient
- greedy algorithm
- control method
- space complexity
- control strategies
- feedback control
- iterative learning control
- worst case scenario
- real time
- control theory
- reinforcement learning algorithms
- markov chain
- multi agent
- learning algorithm