MQLV: Optimal Policy of Money Management in Retail Banking with Q-Learning.
Jérémy CharlierGaston OrmazabalRadu StateJean HilgerPublished in: MIDAS@PKDD (2019)
Keyphrases
- sufficient conditions
- optimal policy
- retail banking
- decision problems
- markov decision processes
- finite horizon
- commercial banks
- infinite horizon
- long run
- multistage
- state dependent
- policy iteration
- average reward
- markov decision process
- average cost
- knowledge management
- project management
- learning algorithm
- dynamic programming
- reinforcement learning
- customer relationship management
- action selection
- state space
- optimal control
- lost sales
- customer churn