AI Paper Atlas

Research map / Bandits and online learning / RL theory and MDPs

Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints

Tianhao Wang, Dongruo Zhou, Quanquan Gu

NeurIPS 2021 · Bandits and online learning › RL theory and MDPs · approach: Linear function approximation in RL · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
limit adaptivity to B=sqrt(K) batches instead of full adaptivityLSVI-UCB-Batch · Hard-to-learn linear MDP (H=10, K=2500, d=13)average regretNo clear effect
use rare-switch policy updates with constant eta instead of updating every episodeLSVI-UCB-RareSwitch · Hard-to-learn linear MDP (H=10, K=2500, d=13)average regretNo clear effect
use rare-switch updates instead of fixed-batch updatesLSVI-UCB-RareSwitch vs Batch · Hard-to-learn linear MDP (H=10, K=2500, d=13)regret gap to LSVI-UCBImproved
decrease number of batches B (10 to 50 tested) (ablation)LSVI-UCB-Batch · Hard-to-learn linear MDP (H=10, K=2500, d=13)average regretHurt
increase switching threshold eta (2 to 32 tested) (ablation)LSVI-UCB-RareSwitch · Hard-to-learn linear MDP (H=10, K=2500, d=13)average regretHurt
compare against uniformly random policyLSVI-UCB-Batch and RareSwitch · Hard-to-learn linear MDP (H=10, K=2500, d=13)average regretImproved
introduce model misspecification zeta = 0.05, 0.1, 0.2, 0.4 (ablation)LSVI-UCB-Batch (B=50), RareSwitch (eta=8) · Misspecified linear MDPaverage regretMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy