AI Paper Atlas

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

Tractable Optimality in Episodic Latent MABs

Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor

NeurIPS 2022 · Bandits and online learning › RL theory and MDPs · approach: Linear function approximation in RL · 0 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
add EM refinement on top of tensor-decomposition initializationtensor-decomposition baseline · Synthetic LMAB, M=7, A=50, N=100000per time-step rewardImproved
increase number of latent contexts M from 4 to 7ED+MLE and L-UCRL+EM · Synthetic LMAB, rank about 4per time-step rewardNo clear effect
increase number of contexts M with fixed A=50, H=7pure tensor-decomposition method · Synthetic LMAB, rank about 4per time-step rewardHurt
increase sampled episodes N with M=5ED+MLE and L-UCRL+EM · Synthetic LMAB, M=5per time-step reward relative to genie policyImproved
use context-aware ED+MLE instead of naive UCB ignoring contextsnaive UCB · Synthetic LMAB, M=4, A=20, N=5e4per time-step rewardImproved
increase episode length HED+MLE, L-UCRL, tensor methods · Synthetic LMAB, M=4per time-step rewardImproved
tensor decomposition alone when covariance is full rank (M=4)tensor-decomposition method · Synthetic LMAB, M=4, A=20per time-step rewardNo clear effect

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