On the Value of Interaction and Function Approximation in Imitation Learning.
Nived RajaramanYanjun HanLin YangJingbo LiuJiantao JiaoKannan RamchandranPublished in: NeurIPS (2021)
Keyphrases
- function approximation
- imitation learning
- reinforcement learning
- temporal difference
- reinforcement learning algorithms
- reinforcement learning methods
- state space
- learning tasks
- radial basis function
- control problems
- maximum margin
- model free
- function approximators
- machine learning
- humanoid robot
- robotic systems
- supervised learning
- multi agent
- computer vision
- learning algorithm
- optimal control
- markov decision processes
- optimal policy
- support vector