Develops and tests the first effective safeguard for analytic gradient-based provably safe RL, showing safe training on three control tasks without performance loss.
Monte carlo gradient estimation in machine learning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A co-optimization framework for power system capacity and demand-shaping policies that uses differentiable scenario generation from generative machine learning models.
citing papers explorer
-
Leveraging Analytic Gradients in Provably Safe Reinforcement Learning
Develops and tests the first effective safeguard for analytic gradient-based provably safe RL, showing safe training on three control tasks without performance loss.
-
Integrated Investment and Policy Planning for Power Systems via Differentiable Scenario Generation
A co-optimization framework for power system capacity and demand-shaping policies that uses differentiable scenario generation from generative machine learning models.