Normalization and effective learning rates in reinforcement learning.
Clare LyleZeyu ZhengKhimya KhetarpalJames MartensHado van HasseltRazvan PascanuWill DabneyPublished in: CoRR (2024)
Keyphrases
- effective learning
- reinforcement learning
- learning process
- learning path
- function approximation
- e learning
- learning algorithm
- state space
- optimal policy
- learning content
- model free
- machine learning
- learning styles
- multi agent
- learning strategies
- learning experience
- markov decision processes
- distance learning
- active learning
- online discussion
- semi supervised
- learning systems