Waiting or Moving? A Crossroad Network-Based Markov Decision Process Approach to Catch Vacant Taxis.
Huigui RongXudong ZhangZhuo LiZhaoyang AiPublished in: IEEE Access (2020)
Keyphrases
- markov decision process
- state space
- markov decision processes
- reinforcement learning
- infinite horizon
- optimal policy
- finite horizon
- policy iteration
- moving objects
- road network
- transition matrices
- initial state
- dynamic programming
- real time
- search engine
- transition probabilities
- reward function
- single server
- higher order
- search algorithm