An Iterative and Starvation-Free Solution for a General Class of Distributed Control Problems Based on Interaction Primitives.
Horst F. WeddePublished in: Theor. Comput. Sci. (1983)
Keyphrases
- control problems
- reinforcement learning
- optimal control
- special case
- hamilton jacobi bellman
- iterative methods
- distributed systems
- human computer interaction
- mathematical model
- optimal solution
- queueing systems
- multi agent
- closed form
- dynamic programming
- closed form solutions
- adaptive control
- stochastic control
- learning algorithm