Reinforcement Learning of Supply Chain Control Policy Using Closed Loop Multi-agent Simulation.
Souvik BaratPrashant KumarMonika GajraniHarshad KhadilkarHardik MeisheriVinita BaniwalVinay KulkarniPublished in: MABS (2019)
Keyphrases
- control policy
- closed loop
- supply chain
- multi agent simulation
- reinforcement learning
- multi agent
- open loop
- supply chain management
- control system
- control law
- control scheme
- control policies
- feedback control
- long run
- bullwhip effect
- function approximation
- asymptotic stability
- profit sharing
- state space
- lead time
- model free
- service level
- optimal policy
- markov decision processes
- optimal control
- pid controller
- decision making
- learning algorithm
- action space
- special case
- computational complexity
- expected profit
- data mining
- neural network