Towards Dynamic Pricing for Shared Mobility on Demand using Markov Decision Processes and Dynamic Programming.
Yue GuanAnuradha M. AnnaswamyH. Eric TsengPublished in: ITSC (2020)
Keyphrases
- markov decision processes
- dynamic pricing
- dynamic programming
- optimal policy
- state space
- supply chain management
- infinite horizon
- finite state
- inventory level
- policy iteration
- transition matrices
- learning curve
- average cost
- reinforcement learning
- markov decision process
- linear programming
- average reward
- multistage
- finite horizon
- action space
- decision theoretic planning
- linear program
- reward function
- partially observable
- data mining
- optimal control
- random variables