conftrace_

risk criterion

4 papers

Explore in graph

Co-occurring keywords

multi-armed bandit (1098) conditional value-at-risk (28) regret bound (1926) multinomial logit bandit (2) entropy risk (1) non-stationary learning (19) stochastic bandit (98) sharpe ratio (8) heavy-tailed distribution (98) atari game (36)

Papers

Piecewise Stationary Bandits under Risk Criteria AISTATS 2023
Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion NIPS 2023
Near-Optimal MNL Bandits Under Risk Criteria AAAI 2021
A General Approach to Multi-Armed Bandits Under Risk Criteria COLT 2018