Forward and inverse reinforcement learning sharing network weights and hyperparameters.
Eiji UchibeKenji DoyaPublished in: Neural Networks (2021)
Keyphrases
- hyperparameters
- inverse reinforcement learning
- model selection
- cross validation
- bayesian framework
- gaussian processes
- gaussian process
- posterior distribution
- random sampling
- bayesian inference
- closed form
- support vector
- machine learning
- sample size
- incremental learning
- missing data
- upper bound
- evolutionary algorithm
- artificial neural networks
- search algorithm
- preference elicitation
- objective function