Modeling Freight-Sharing Platform Operations for Optimal Compensation Strategy Using Markov Decision Processes.
Siqi ShuZhengqi ChenZhe YuShaosheng CaoGuobin WuDonghai ShiGaoang WangZuozhu LiuXiqun ChenXiaoxiang NaChao WuSimon HuPublished in: ITSC (2022)
Keyphrases
- markov decision processes
- dynamic programming
- sharing platform
- average cost
- finite horizon
- average reward
- finite state
- action sets
- transition matrices
- optimal strategy
- policy iteration
- optimal policy
- reinforcement learning
- decision theoretic planning
- stationary policies
- state space
- partially observable
- markov decision process
- action space
- discounted reward
- long run
- infinite horizon
- conceptual framework
- total reward
- machine learning
- data mining
- power grid
- computational intelligence
- search space
- metadata