RePreM: Representation Pre-training with Masked Model for Reinforcement Learning.
Yuanying CaiChuheng ZhangWei ShenXuyun ZhangWenjie RuanLongbo HuangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- probability distribution
- computational model
- conceptual model
- experimental data
- management system
- representation scheme
- probabilistic model
- mobile robot
- em algorithm
- theoretical analysis
- dynamic programming
- theoretical framework
- prior knowledge
- machine learning
- function approximation
- data sets