conftrace_

optimal reward

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

online gradient ascent (1) agent limitations (1) algorithm (1) regret bound (1) stochastic method (1) gradient ascent (1) approximation factor (1) single stream (1) concave reward functions (1) improving multi-armed bandits (1)

Papers

Nearly-tight Approximation Guarantees for the Improving Multi-Armed Bandits Problem ALT 2025 Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning ICML 2013 Reward Design via Online Gradient Ascent NeurIPS 2010