https://openreview.net/forum?id=9JFSJitKC0&referrer=%5Bthe%20profile%20of%20Seungyub%20Han%5D(%2Fprofile%3Fid%3D~Seungyub_Han1)
The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly...
safe reinforcement learningspectralriskconvergenceguarantees
https://openreview.net/forum?id=AuwUAbXohW&referrer=%5Bthe%20profile%20of%20Alan%20Fern%5D(%2Fprofile%3Fid%3D~Alan_Fern1)
Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy...
safe reinforcement learningconstraintadaptivepolicyswitching
https://www.sml-group.cc/blog/2023-safe-sampling/
Background Model-based reinforcement learning (MBRL) approaches learn a dynamics model from system interaction data and use it as a proxy of the physical...
reinforcement learningsafetrajectorysamplingmodel
https://deepai.org/publication/approximate-model-based-shielding-for-safe-reinforcement-learning
07/27/23 - Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains. However, applying RL to s...
safe reinforcement learningapproximatemodelbasedshielding