Percentile Criterion Optimization in Offline Reinforcement Learning.
Cyrus CousinsElita LoboMarek PetrikYair ZickPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- optimization process
- real time
- global optimization
- optimal policy
- optimization problems
- state space
- multi agent
- decision trees
- combinatorial optimization
- function approximation
- constrained optimization
- optimization algorithm
- optimization method
- optimization methods
- optimization model
- model free
- temporal difference
- reinforcement learning algorithms
- supervised learning
- mobile robot
- similarity measure
- genetic algorithm
- machine learning