Minimizing conditional value-at-risk instead of worst-case performance reduces conservatism in robust H2/H-infinity control by tolerating rare degradations for better average behavior.
Optimizing the CVaR via Sampling
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Conditional Value at Risk (CVaR) is a prominent risk measure that is being used extensively in various domains. We develop a new formula for the gradient of the CVaR in the form of a conditional expectation. Based on this formula, we propose a novel sampling-based estimator for the CVaR gradient, in the spirit of the likelihood-ratio method. We analyze the bias of the estimator, and prove the convergence of a corresponding stochastic gradient descent algorithm to a local CVaR optimum. Our method allows to consider CVaR optimization in new domains. As an example, we consider a reinforcement learning application, and learn a risk-sensitive controller for the game of Tetris.
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
DR-Gym is a new Gymnasium-compatible simulator for training utility demand-response policies with regime-switching wholesale prices and physics-based building demand.
The paper categorizes five concrete AI safety problems arising from flawed objectives, costly evaluation, and learning dynamics.
citing papers explorer
-
Robust H2/H-infinity control under stochastic requirements: minimizing conditional value-at-risk instead of worst-case performance
Minimizing conditional value-at-risk instead of worst-case performance reduces conservatism in robust H2/H-infinity control by tolerating rare degradations for better average behavior.
-
Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs
DR-Gym is a new Gymnasium-compatible simulator for training utility demand-response policies with regime-switching wholesale prices and physics-based building demand.
-
Concrete Problems in AI Safety
The paper categorizes five concrete AI safety problems arising from flawed objectives, costly evaluation, and learning dynamics.