A multi-agent reinforcement learning approach to obtaining dynamic control policies for stochastic lot scheduling problem.
Carlos D. Paternina-ArboledaTapas K. DasPublished in: Simul. Model. Pract. Theory (2005)
Keyphrases
- control policies
- multi agent reinforcement learning
- scheduling problem
- reinforcement learning
- stochastic optimization problems
- optimal policy
- multi agent
- np hard
- control policy
- control system
- dynamic environments
- motion control
- control strategies
- multi agent systems
- mobile robot
- action space
- complex environments
- stochastic games