Constrained adaptive optimal control using a reinforcement learning agent.
Wei-Song LinChen-Hong ZhengPublished in: Autom. (2012)
Keyphrases
- optimal control
- reinforcement learning
- learning agent
- learning capabilities
- state space
- dynamic programming
- reinforcement learning algorithms
- optimal control problems
- function approximation
- multi agent
- learning algorithm
- control strategy
- solving problems
- markov decision processes
- temporal difference
- model free
- learning strategies
- learning process
- transfer learning
- optimal policy
- knowledge base
- decision making