Near-minimax-optimal risk-sensitive reinforcement learning with cvar
In this paper, we study risk-sensitive Reinforcement Learning (RL), focusing on the objective
of Conditional Value at Risk (CVaR) with risk tolerance $\tau $. Starting with multi-arm …
of Conditional Value at Risk (CVaR) with risk tolerance $\tau $. Starting with multi-arm …
Optimal thompson sampling strategies for support-aware cvar bandits
In this paper we study a multi-arm bandit problem in which the quality of each arm is
measured by the Conditional Value at Risk (CVaR) at some level alpha of the reward …
measured by the Conditional Value at Risk (CVaR) at some level alpha of the reward …
Off-policy risk assessment in contextual bandits
Even when unable to run experiments, practitioners can evaluate prospective policies, using
previously logged data. However, while the bandits literature has adopted a diverse set of …
previously logged data. However, while the bandits literature has adopted a diverse set of …
[PDF][PDF] Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions
LA Prashanth, K Jagannathan… - Proceedings of the 37th …, 2020 - proceedings.mlr.press
Abstract Conditional Value-at-Risk (CVaR) is a widely used risk metric in applications such
as finance. We derive concentration bounds for CVaR estimates, considering separately the …
as finance. We derive concentration bounds for CVaR estimates, considering separately the …
Nearly optimal catoni's m-estimator for infinite variance
In this paper, we extend the remarkable M-estimator of Catoni\citep {Cat12} to situations
where the variance is infinite. In particular, given a sequence of iid random variables $\{X_i\} …
where the variance is infinite. In particular, given a sequence of iid random variables $\{X_i\} …
Sample-based bounds for coherent risk measures: Applications to policy synthesis and verification
Autonomous systems are increasingly used in highly variable and uncertain environments
giving rise to the pressing need to consider risk in both the synthesis and verification of …
giving rise to the pressing need to consider risk in both the synthesis and verification of …
Adaptive best-of-both-worlds algorithm for heavy-tailed multi-armed bandits
In this paper, we generalize the concept of heavy-tailed multi-armed bandits to adversarial
environments, and develop robust best-of-both-worlds algorithms for heavy-tailed multi …
environments, and develop robust best-of-both-worlds algorithms for heavy-tailed multi …
Truthful user recruitment for cooperative crowdsensing task: A combinatorial multi-armed bandit approach
Mobile Crowdsensing (MCS) is a promising paradigm that recruits users to cooperatively
perform a sensing task. When recruiting users, existing works mainly focus on selecting a …
perform a sensing task. When recruiting users, existing works mainly focus on selecting a …
[PDF][PDF] Optimal algorithms for stochastic multi-armed bandits with heavy tailed rewards
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards Page 1
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards Kyungjae Lee …
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards Kyungjae Lee …
Optimal best-arm identification methods for tail-risk measures
S Agrawal, WM Koolen… - Advances in Neural …, 2021 - proceedings.neurips.cc
Conditional value-at-risk (CVaR) and value-at-risk (VaR) are popular tail-risk measures in
finance and insurance industries as well as in highly reliable, safety-critical uncertain …
finance and insurance industries as well as in highly reliable, safety-critical uncertain …