trends.barnas.net

method · first seen 22 Oct 2026

maximum entropy inverse reinforcement learning

Also: MaxEnt IRL

Inferring a reward function from demonstrations by choosing the distribution of maximum entropy consistent with feature expectations.

Mentions per week

0219 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

traversability estimationBradley-Terry modelmulti-agent inverse reinforcement learning