Imitation Learning with Demonstrations and Shaping Rewards.
Kshitij JudahAlan FernPrasad TadepalliRobby GoetschalckxPublished in: AAAI (2014)
Keyphrases
- imitation learning
- reinforcement learning
- reward shaping
- markov decision processes
- reinforcement learning algorithms
- state space
- robotic systems
- function approximation
- reinforcement learning methods
- control problems
- maximum margin
- humanoid robot
- reward function
- model free
- machine learning
- learning algorithm
- temporal difference
- transfer learning
- optimal policy
- logic programs
- graphical models
- video sequences
- data points
- dynamic programming
- computer vision
- support vector