Optimizing Taxi Carpool Policies via Reinforcement Learning and Spatio-Temporal Mining.
Ishan JindalZhiwei (Tony) QinXuewen ChenMatthew S. NoklebyJieping YePublished in: IEEE BigData (2018)
Keyphrases
- spatio temporal
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- control policies
- knowledge discovery
- data mining
- function approximation
- reward function
- spatial and temporal
- spatio temporal data
- model free
- mining algorithm
- decision problems
- web mining
- markov decision processes
- data mining techniques
- reinforcement learning agents
- space time
- finite state
- web logs
- moving objects
- spatio temporal databases
- learning algorithm
- reinforcement learning algorithms
- partially observable markov decision processes
- machine learning
- multiagent reinforcement learning
- fitted q iteration
- temporal difference
- action selection
- human motion
- dynamical systems
- state space
- multi agent