Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models.
Viktor BengsAadirupa SahaEyke HüllermeierPublished in: ICML (2022)
Keyphrases
- stochastic models
- stochastic systems
- stochastic model
- stochastic process
- stochastic optimization
- stochastic processes
- monte carlo
- statistical models
- linear model
- stochastic inventory control
- linear gaussian
- nonlinear models
- linear models
- contextual information
- probabilistic model
- prior knowledge
- multi armed bandit
- neural network
- experimental data
- simple linear
- artificial neural networks
- objective function
- semi markov
- nonlinear regression
- reinforcement learning
- information retrieval