AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning

Ofir Marom, Benjamin Rosman

NeurIPS 2018 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Robust fine-tuning of zero-shot models · 1 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
use deictic instead of propositional representation as passengers increaseDOORMAX OO-MDP learner · All-passenger any-destination Taxiaverage test stepsImproved
transfer previously learned transition dynamics when increasing passengers n (ablation)Deictic OO-MDP · Taxi, n = 4average test stepsImproved
no transfer (relearn dynamics for each n) (ablation)Deictic OO-MDP · Taxi, n = 4 to n = 5 larger gridworldsteps relative to optimalHurt
zero-shot transfer dynamics from toy Sokoban MDP to large Sokoban taskDeictic OO-MDP · Sokoban Micro-Cosmossteps to solve: 209Improved

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