Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning.
De-An HuangDanfei XuYuke ZhuAnimesh GargSilvio SavareseLi Fei-FeiJuan Carlos NieblesPublished in: CoRR (2019)
Keyphrases
- imitation learning
- continuous relaxation
- knapsack problem
- mixed integer
- higher dimensional
- maximum margin
- linear programming
- robotic systems
- reinforcement learning
- quadratic program
- humanoid robot
- feasible solution
- linear program
- np hard
- optimal solution
- feature selection
- learning algorithm
- convex hull
- dynamic programming
- bayesian networks