Bayesian Imitation Learning for End-to-End Mobile Manipulation.
Yuqing DuDaniel HoAlex AlemiEric JangMohi KhansariPublished in: ICML (2022)
Keyphrases
- end to end
- imitation learning
- robotic systems
- reinforcement learning
- maximum margin
- humanoid robot
- maximum likelihood
- bayesian networks
- congestion control
- admission control
- bayesian inference
- transport layer
- training data
- application layer
- pattern classification
- dynamical systems
- reinforcement learning methods
- state space