conftrace_

policy elimination

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

contextual bandit (2) regret bound (2) reinforcement learning (2) adaptivity constraint (1) root-n regret (1) batch complexity (1) corruption robust algorithm (1) tabular setting (1) reward corruption (1) bellman rank (1)

Papers

Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints ICML 2024 Improved Corruption Robust Algorithms for Episodic Reinforcement Learning ICML 2021 Generalized Policy Elimination: an efficient algorithm for Nonparametric Contextual Bandits UAI 2020 Root-n-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank COLT 2020