Online exploratory behavior acquisition model based on reinforcement learning.
Manabu GoukoYuichi KobayashiChyon Hae KimPublished in: Appl. Intell. (2015)
Keyphrases
- reinforcement learning
- model free
- online learning
- reinforcement learning algorithms
- function approximation
- multi agent
- state space
- data driven
- optimal policy
- data acquisition
- balancing exploration and exploitation
- database
- robotic control
- behavior analysis
- temporal difference
- optimal control
- hidden markov models
- learning process
- case study
- machine learning
- real time