Joint Differentiable Optimization and Verification for Certified Reinforcement Learning.
Yixuan WangSimon Sinong ZhanZhilu WangChao HuangZhaoran WangZhuoran YangQi ZhuPublished in: ICCPS (2023)
Keyphrases
- reinforcement learning
- joint optimization
- optimization problems
- machine learning
- optimization process
- function approximation
- optimization method
- optimization algorithm
- neural network
- model checking
- loss function
- pairwise
- multi agent
- global optimization
- objective function
- temporal difference learning
- least squares
- state space
- dynamic programming
- optimization methods
- learning algorithm
- constrained optimization
- temporal difference
- data sets
- optimization strategies