Reinforcement Learning for on-line Sequence Transformation.
Grzegorz RypescLukasz LepakPawel WawrzynskiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- hidden state
- function approximation
- machine learning
- artificial intelligence
- real time
- action selection
- markov decision processes
- supervised learning
- learning process
- multi agent
- similarity measure
- evolutionary algorithm
- case study
- decision making
- learning algorithm
- databases
- temporal difference
- sequence analysis
- stochastic approximation
- database
- transition model
- robotic control