Adaptive deep Q learning network with reinforcement learning for crime prediction.
J. Vimala DeviK. S. KavithaPublished in: Evol. Intell. (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- multi agent
- learning algorithm
- state space
- action selection
- model free
- temporal difference
- actor critic
- markov decision processes
- optimal policy
- criminal networks
- prediction accuracy
- radial basis function network
- temporal difference learning
- continuous state and action spaces
- crime prevention
- cooperative
- reinforcement learning methods
- network structure
- learning capabilities
- reward function
- prediction error
- stochastic approximation
- traffic signal
- multi agent reinforcement learning
- machine learning