Julian Skirzyński
Julian Skirzyński
Home
Publications
CV
2
Boosting human decision-making with AI-generated decision aids
Here, we test if planning strategies discovered automatically through our reinforcement learning pipeline from
this work
can improve …
Frederic Becker
,
Julian Skirzyński
,
Bas van Opheusden
,
Falk Lieder
PDF
Cite
Code
Dataset
DOI
Automatic discovery of interpretable planning strategies
We present an imitation learning method for generating an intepretable description of any RL policy in form of a decision tree. We also apply that method in our pipeline for discovering clever decision heuristics using RL, and show how people’s decision making improves when they use the automatically found decsriptions as decision aids.
Julian Skirzyński
,
Frederic Becker
,
Falk Lieder
PDF
Cite
Code
Dataset
Cite
×