Model-Free Deep Inverse Reinforcement Learning by Logistic Regression.
Eiji UchibePublished in: Neural Process. Lett. (2018)
Keyphrases
- model free
- logistic regression
- inverse reinforcement learning
- temporal difference
- reinforcement learning
- belief nets
- reward function
- reinforcement learning algorithms
- decision trees
- function approximation
- policy iteration
- preference elicitation
- support vector
- naive bayes
- loss function
- dynamic programming
- data sets
- partially observable
- machine learning
- supervised learning
- knn
- active learning
- feature extraction
- neural network