Genetic Imitation Learning by Reward Extrapolation.
Boyuan ZhengJianlong ZhouFang ChenPublished in: CoRR (2023)
Keyphrases
- imitation learning
- reinforcement learning
- robotic systems
- humanoid robot
- genetic algorithm
- maximum margin
- state space
- function approximation
- model free
- reinforcement learning methods
- average reward
- training set
- machine learning
- long run
- computer vision
- temporal difference
- reward function
- reinforcement learning algorithms
- control problems
- pattern classification
- optimal policy
- dynamic programming