Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow.
Xue Bin PengAngjoo KanazawaSam ToyerPieter AbbeelSergey LevinePublished in: CoRR (2018)
Keyphrases
- information flow
- imitation learning
- reinforcement learning
- social networks
- reinforcement learning methods
- communication networks
- information security
- function approximation
- humanoid robot
- state space
- robotic systems
- multi agent
- reinforcement learning algorithms
- image segmentation
- markov decision processes
- multi modal
- model free
- dynamic programming
- machine learning