Evacuation route recommendation using auto-encoder and Markov decision process.
Chongke BiGuosheng PanLu YangChun-Cheng LinMin HouYuanqi HuangPublished in: Appl. Soft Comput. (2019)
Keyphrases
- markov decision process
- state space
- optimal policy
- reinforcement learning
- markov decision processes
- recommender systems
- collaborative filtering
- finite horizon
- infinite horizon
- initial state
- transition matrices
- multi agent
- bit rate
- road network
- reward function
- policy iteration
- transition probabilities
- data mining
- higher order
- objective function
- decision problems
- model checking