AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Provably Efficient Learning of Transferable Rewards

Alberto Maria Metelli, Giorgia Ramponi, Alessandro Concetti, Marcello Restelli

ICML 2021 · Reinforcement learning › Imitation learning · approach: Reward learning from demonstrations · 2 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
adding a meaningful IRL reward-selection criterion (MaxGap, Linear, MaxEnt) instead of random selection from the feasible set (ablation)TRAVEL · Random MDPsperformance gap ||V*_rE - V^pi*_rE||_2^2Improved
active sampling (TRAVEL) instead of uniform samplingIRL with generative model · Chain MDPperformance gap ||V*_rE - V^pi*_rE||_2^2: near-optimal performance in less than half the samplesImproved
active sampling (TRAVEL) instead of uniform samplingIRL with generative model · Chain MDPperformance gap at small sample countsMixed
IRL (reward transfer) instead of behavioral cloningpolicy transfer to target environment · Gridworld with varying obstacle probabilityperformance gap in target MDPImproved
random reward selection from feasible set (Random-IRL) instead of meaningful criterion (ablation)TRAVEL · Random MDPsperformance gapHurt

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