Stochastic Processes for Return Maximization in Reinforcement Learning.
Kazunori IwataHideaki SakaiKazushi IkedaPublished in: ICANN (2) (2005)
Keyphrases
- stochastic processes
- reinforcement learning
- action space
- stochastic process
- probability distribution
- stochastic models
- random fields
- markov processes
- dynamic bayesian networks
- brownian motion
- random variables
- optimal policy
- machine learning
- optimal control
- state space
- particle filtering
- continuous time bayesian networks
- markov decision processes
- transfer learning
- optical flow
- social networks
- learning algorithm