Skip to content
conftrace_

undiscounted setting

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

regret bound (2) posterior sampling (1) exploration-exploitation tradeoff (1) exploration exploitation (1) optimal policy (1) multi-armed bandit (1) upper confidence bound (1) undiscounted reinforcement learning (1) online regret bound (1) cmdp (1)

Papers

Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling ICML 2024 Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning NeurIPS 2006