Unsupervised Perceptual Rewards for Imitation Learning.
Pierre SermanetKelvin XuSergey LevinePublished in: Robotics: Science and Systems (2017)
Keyphrases
- imitation learning
- reinforcement learning
- robotic systems
- supervised learning
- unsupervised learning
- maximum margin
- humanoid robot
- machine learning
- state space
- function approximation
- learning algorithm
- reward function
- semi supervised
- markov decision processes
- hyperplane
- model free
- transfer learning
- reinforcement learning algorithms
- mobile robot