Learning of Nash Equilibria in Risk-Averse Games
Preprint
Abstract
This paper considers risk-averse learning in convex games involving multiple agents that aim to minimize their individual risk of incurring significantly high costs. Specifically, the agents adopt the conditional value at risk (CVaR) as a risk measure with possibly different risk levels. To solve this problem, we propose a first-order risk-averse leaning algorithm, in which the CVaR gradient estimate depends on an estimate of the Value at Risk (VaR) value combined with the gradient of the stochastic cost function. Although estimation of the CVaR gradients using finitely many samples is generally biased, we show that the accumulated error of the CVaR gradient estimates is bounded with high probability. Moreover, assuming that the risk-averse game is strongly monotone, we show that the proposed algorithm converges to the risk-averse Nash equilibrium. We present numerical experiments on a Cournot game example to illustrate the performance of the proposed method.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit FeedbackOperations Research, 2025
- Risk-Averse Control via CVaR Barrier Functions: Application to Bipedal Robot LocomotionIEEE Control Systems Letters, 2021
- Learning Generalized Nash Equilibria in a Class of Convex GamesIEEE Transactions on Automatic Control, 2018
- Learning in games with continuous action sets and unknown payoff functionsMathematical Programming, 2018
- A Note on Quantiles in Large SamplesThe Annals of Mathematical Statistics, 1966