AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Provable Defense against Backdoor Policies in Reinforcement Learning

Shubham Kumar Bharti, Xuezhou Zhang, Adish Singla, Jerry Zhu

NeurIPS 2022 · Reinforcement learning › MDPs and planning · approach: Rich-observation exploration · 7 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
sanitize backdoor policy by projecting states onto safe subspace using n clean samplesbackdoor policy (Boxing-Ram, Breakout) · triggered environmentmean empirical returnImproved
increase number of clean sanitization samples n (ablation)sanitized policy · Boxing-Ram and Breakoutmean empirical returnImproved
underestimate safe subspace dimension d (ablation)sanitized policy · Boxing-Ram and Breakoutmean empirical returnHurt
overestimate safe subspace dimension d (ablation)sanitized policy · Boxing-Ram and Breakoutmean empirical returnHurt
use roughly 2n correlated samples instead of n independent samples (ablation)sanitization algorithm · Boxing-Ram and Breakoutmean empirical returnNo 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