Policy Poisoning in Batch Reinforcement Learning and Control.
Yuzhe MaXuezhou ZhangWen SunXiaojin ZhuPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- control policy
- optimal policy
- action selection
- control policies
- control problems
- policy search
- batch mode
- robotic control
- robot control
- optimal control
- state space
- adaptive control
- machine learning
- supervised learning
- reinforcement learning algorithms
- function approximation
- approximate dynamic programming
- state and action spaces
- learning algorithm
- model free
- partially observable
- control method
- control strategy
- learning problems
- actor critic
- mobile robot