Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow.
Xue Bin PengAngjoo KanazawaSam ToyerPieter AbbeelSergey LevinePublished in: ICLR (Poster) (2019)
Keyphrases
- information flow
- imitation learning
- reinforcement learning
- information security
- social networks
- reinforcement learning methods
- communication networks
- robotic systems
- control problems
- maximum margin
- supply chain
- function approximation
- machine learning
- markov decision processes
- multi agent
- data mining
- mobile robot
- temporal difference
- action space
- decision making
- image segmentation