Distributional Robustness and Regularization in Reinforcement Learning.
Esther DermanShie MannorPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- co occurrence
- learning process
- temporal difference
- regularization method
- dynamic programming
- state space
- optimal policy
- prior information
- model free
- multi agent reinforcement learning
- data sets
- regularization framework
- supervised learning
- learning algorithm
- machine learning
- neural network