Continuous-Time Reinforcement Learning: New Design Algorithms with Theoretical Insights and Performance Guarantees.
Brent A. WallaceJennie SiPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- theoretical insights
- learning algorithm
- function approximation
- orders of magnitude
- computational efficiency
- times faster
- efficient implementation
- machine learning
- computational complexity
- benchmark datasets
- data structure
- optimal solution
- optimal control
- multi agent systems
- computational cost
- optimization problems
- markov decision processes