Policy Poisoning in Batch Reinforcement Learning and Control.
Yuzhe MaXuezhou ZhangWen SunJerry ZhuPublished in: NeurIPS (2019)
Keyphrases
- reinforcement learning
- control policy
- action selection
- control problems
- optimal policy
- batch mode
- optimal control
- control policies
- policy search
- control system
- function approximation
- stochastic control
- state space
- robot control
- action space
- control strategies
- markov decision process
- function approximators
- policy iteration
- policy evaluation
- partially observable
- temporal difference
- infinite horizon
- markov decision processes
- dynamic programming
- robotic control
- approximate dynamic programming
- state and action spaces
- reinforcement learning algorithms
- machine learning
- reward function
- adaptive control
- control method
- learning algorithm