Generate and Revise: Reinforcement Learning in Neural Poetry.
Andrea ZugariniLuca PasqualiniStefano MelacciMarco MagginiPublished in: IJCNN (2021)
Keyphrases
- reinforcement learning
- fitted q iteration
- neural network
- network architecture
- multi agent
- optimal policy
- evolutionary algorithm
- state space
- markov decision processes
- function approximation
- automatically generate
- neural fuzzy
- learning algorithm
- learning process
- learning rules
- neural model
- autonomous learning
- robotic control
- real time