Social Conformity and Its Convergence for Reinforcement Learning.
Juan Ángel García-PardoJosé SolerCarlos CarrascosaPublished in: MATES (2010)
Keyphrases
- reinforcement learning
- stochastic approximation
- social networks
- social interaction
- function approximation
- learning algorithm
- machine learning
- social influence
- convergence speed
- robotic control
- policy search
- social networking
- convergence rate
- state space
- optimal policy
- dynamic programming
- faster convergence
- model free
- social capital
- learning process
- action selection
- reinforcement learning algorithms
- social networking sites
- data sets
- objective function
- multi agent
- markov decision processes
- collective intelligence
- optimal control
- online social networks
- transfer learning