Skip to content
conftrace_

undiscounted reinforcement learning

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

regret bound (2) reinforcement learning algorithm (1) online regret bound (1) heavy-tailed reward (1) robust mean estimation (1) heavy-tailed distribution (1) upper confidence bound (1) multi-armed bandit (1) robust estimation (1) optimal policy (1)

Papers

No-Regret Reinforcement Learning with Heavy-Tailed Rewards AISTATS 2021 Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning NeurIPS 2006