Adaptive Adversarial Training for Meta Reinforcement Learning.
Shiqi ChenZhengyu ChenDonglin WangPublished in: IJCNN (2021)
Keyphrases
- reinforcement learning
- multi agent
- training set
- function approximation
- learning algorithm
- dynamic programming
- supervised learning
- training process
- markov decision processes
- machine learning
- reinforcement learning algorithms
- adaptive control
- training examples
- multi agent reinforcement learning
- state space
- model free
- robotic control
- test set
- database
- hidden markov models
- feature space
- support vector
- data sets