Reducing the Planning Horizon Through Reinforcement Learning.
Logan DunbarBenjamin RosmanAnthony G. CohnMatteo LeonettiPublished in: ECML/PKDD (4) (2022)
Keyphrases
- planning horizon
- reinforcement learning
- multi period
- lot sizing
- production planning
- supply chain
- expected cost
- total cost
- lead time
- capacity expansion
- production system
- service level
- lot size
- random variables
- optimal production
- optimal policy
- dynamic programming
- learning algorithm
- state space
- machine learning
- long run
- optimal control
- production cost
- markov decision processes
- markov decision process
- knapsack problem
- cost function