conftrace_

greedy policy

12 papers

Explore in graph

Co-occurring keywords

multi-armed bandit (1098) regret bound (1926) approximation guarantee (65) adaptive submodularity (11) policy iteration (99) mutual information (724) action-gap (1) approximate value iteration (7) online reinforcement learning (45) dynamic feature selection (3)

Papers

Learning to Maximize Mutual Information for Dynamic Feature Selection ICML 2023
An Efficient Algorithm for Deep Stochastic Contextual Bandits AAAI 2021
Rebounding Bandits for Modeling Satiation Effects NIPS 2021
Adaptive Submodular Maximization under Stochastic Item Costs COLT 2020
Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies NIPS 2019
Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio ICML 2019
Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning NIPS 2018
Adaptive Submodularity with Varying Query Sets: An Application to Active Multi-label Learning ALT 2017
Global Multi-armed Bandits with Hölder Continuity AISTATS 2015
Sequential Information Maximization: When is Greedy Near-optimal? COLT 2015
Action-Gap Phenomenon in Reinforcement Learning NIPS 2011
On the Convergence of Optimistic Policy Iteration JMLR 2002