Efficient Offline Policy Optimization with a Learned Model.
Zichen LiuSiyi LiWee Sun LeeShuicheng YanZhongwen XuPublished in: ICLR (2023)
Keyphrases
- probabilistic model
- optimization model
- computational model
- theoretical analysis
- cost function
- theoretical framework
- real time
- probability distribution
- learning phase
- conceptual model
- parameter estimation
- em algorithm
- management system
- data structure
- reinforcement learning
- bayesian networks
- similarity measure
- image sequences
- information retrieval
- machine learning