Reinforcement Learning for on-line Sequence Transformation.
Grzegorz RypescLukasz LepakPawel WawrzynskiPublished in: FedCSIS (2022)
Keyphrases
- reinforcement learning
- hidden state
- function approximation
- dynamic programming
- machine learning
- optimal control
- least squares
- robotic control
- temporal difference learning
- linear transformation
- event sequences
- reinforcement learning algorithms
- temporal difference
- databases
- state space
- video sequences
- multi agent
- learning algorithm
- neural network