Joint Differentiable Optimization and Verification for Certified Reinforcement Learning.
Yixuan WangChao HuangZhaoran WangZhuoran YangQi ZhuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- joint optimization
- optimization problems
- optimization algorithm
- objective function
- global optimization
- function approximation
- optimization process
- autonomous learning
- optimization strategies
- reinforcement learning algorithms
- state space
- neural network
- model checking
- temporal difference
- face verification
- differential evolution
- dynamic programming
- support vector
- multi agent
- database systems