Adversarial Exploration Strategy for Self-Supervised Imitation Learning.
Zhang-Wei HongTsu-Jui FuTzu-Yun ShannYi-Hsiang ChangChun-Yi LeePublished in: CoRR (2018)
Keyphrases
- imitation learning
- exploration strategy
- reinforcement learning
- multi agent
- unknown environments
- single agent
- state space
- robotic systems
- function approximation
- learning algorithm
- mobile robot
- optimal policy
- locally optimal
- reinforcement learning algorithms
- temporal difference
- model free
- maximum margin
- machine learning
- real time
- supervised learning
- free space
- markov decision processes
- optimal control
- action space
- graphical models
- dynamic environments