The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning.
Sarah RathnamSonali ParbhooWeiwei PanSusan A. MurphyFinale Doshi-VelezPublished in: ICML (2023)
Keyphrases
- reinforcement learning
- equivalence relationship
- smoothing parameter
- regularization method
- machine learning
- parameter selection
- projection operator
- regularization term
- prior information
- function approximators
- inverse problems
- markov decision processes
- trace norm
- empirical risk minimization
- multi agent
- image segmentation
- learning algorithm