Skip to content
conftrace_

bellman rank

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

function approximation (2) reinforcement learning (2) pac learnable (1) systematic exploration (1) policy elimination (1) root-n regret (1) contextual bandit (1) cumulative regret (1) optimistic exploration (1) markov decision process (1)

Papers

Root-n-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank COLT 2020 Contextual Decision Processes with low Bellman rank are PAC-Learnable ICML 2017