conftrace_

slater's parameter

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

cumulative positive constraints violation (1) stochastic hard constraints (1) adaptive regret minimization (1) sublinear violations (1) weakly adaptive (1) bandits with knapsack (1) adversarial mdp (1) competitive ratio (1) sublinear regret (1) bandit feedback (1)

Papers

Learning Adversarial MDPs with Stochastic Hard Constraints ICML 2025 No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization ICML 2025