AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

The Unreasonable Effectiveness of Inverse Reinforcement Learning in Advancing Cancer Research

John Kalantari, Heidi Nelson, Nicholas Chia

AAAI 2020 · Reinforcement learning › Imitation learning · approach: Reward learning from demonstrations · 15 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
increase number of expert paths in uniform sampling (ablation)PUR-IRL · GridWorld 8x8, 3 expertsF1, NMI, EVD, number of tablesImproved
set discount d=1.0 (heavy fat-tail bias) instead of smaller d (ablation)PUR-IRL · GridWorld 8x8, uniform samplingF1, NMI, number of reward functionsHurt
add discount hyperparameter d>0 to Pitman-Yor prior vs d=0 (DPM-IRL) (ablation)PUR-IRL · GridWorld 8x8, non-uniform power-law samplingF1, NMI, EVDImproved
set d=0, reducing PUR-IRL to DPM-IRL (ablation)PUR-IRL · GridWorld 8x8, uniform samplingF1, NMI, EVDNo clear effect
incrementally integrate new state/action information through pop-up updates (ablation)PUR-IRL · CRC tumor data (27 tumors)posterior probability of reward functionImproved

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