Risk-averse reinforcement learning (RL) seeks to provide a risk-averse policy for high-stakes real-world decision problems. These high-stake domains include autonomous driving (Jin et al., 2019; Sharma et al., 2020), robot collision avoidance (Ahmadi et al., 2021; Hakobyan and Y ang, 2021),

The empirical risk function is the cornerstone of machine learning.

However, the typical bilevel formulation for coreset selection explicitly performs optimization over discrete decision variables with greedy search, which is computationally expensive.

This unified envelope strategy allows for the extension of the algorithms and their convergence guarantees to BO settings.

Figure 2: Diffusion modeling for CO solving where the model learns how to gradually denoise from the random noise to predict each step's