Online Robustness Training for Deep Reinforcement Learning.
Marc FischerMatthew MirmanSteven StalderMartin T. VechevPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- online learning
- online training
- batch mode
- training process
- function approximation
- training phase
- state space
- deep architectures
- learning algorithm
- dynamic programming
- training set
- training examples
- robotic control
- markov decision processes
- robot control
- reinforcement learning algorithms
- balancing exploration and exploitation
- test set
- training algorithm
- transfer learning
- optimal policy
- training samples
- supervised learning
- learning process
- multi agent systems
- social networks