Incremental Stochastic Factorization for Online Reinforcement Learning.
André da Motta Salles BarretoRafael L. BeirigoJoelle PineauDoina PrecupPublished in: AAAI (2016)
Keyphrases
- reinforcement learning
- direct policy search
- batch mode
- function approximation
- incremental learning
- online learning
- real time
- state space
- markov decision processes
- learning automata
- stochastic optimization
- stochastic approximation
- optimal control
- balancing exploration and exploitation
- continuous state spaces
- model free
- incremental version
- online communities
- monte carlo
- collaborative filtering
- active learning
- learning process
- multi agent systems
- multi agent
- website
- data sets