CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity.
Aditya BhattDaniel PalenicekBoris BelousovMax ArgusArtemij AmiranashviliThomas BroxJan PetersPublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- real time
- data mining
- batch mode
- computational efficiency
- real world
- learning algorithm
- multi agent
- preprocessing
- state space
- batch processing
- high efficiency
- function approximation
- dynamic programming
- active learning
- learning process
- search space
- computational complexity
- genetic algorithm
- machine learning
- data sets