Reinforcement Learning using Kernel-Based Stochastic Factorization.
André da Motta Salles BarretoDoina PrecupJoelle PineauPublished in: NIPS (2011)
Keyphrases
- reinforcement learning
- direct policy search
- stochastic approximation
- learning automata
- control policies
- monte carlo
- function approximation
- learning algorithm
- multi agent
- support vector
- temporal difference
- dynamic programming
- reinforcement learning methods
- temporal difference learning
- stochastic optimization
- reinforcement learning algorithms
- neural network
- singular value decomposition
- pairwise
- optimal policy
- state space
- learning classifier systems
- action selection
- learning problems
- stochastic model
- stochastic programming
- support vector machine
- hidden markov models
- robotic control
- machine learning