AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Deep Inverse Q-learning with Constraints

Gabriel Kalweit, Maria Huegle, Moritz Werling, Joschka Boedecker

NeurIPS 2020 · Reinforcement learning › Imitation learning · approach: Reward learning from demonstrations · 4 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 inverse action-value iteration instead of MaxEnt IRLObjectworld · ObjectworldEVD: 11.58 -> 0.09Improved
Use inverse Q-learning instead of MaxEnt IRLObjectworld · ObjectworldEVD: 11.58 -> 1.47Improved
Use inverse action-value iteration instead of MaxEnt IRLObjectworld · Objectworldruntime: \SI{8.08}{\hour} -> \SI{1.77}{\minute}Improved
Use inverse Q-learning instead of MaxEnt IRLObjectworld · Objectworldruntime: \SI{8.08}{\hour} -> \SI{21.06}{\minute}Improved
Use a single inner value-iteration step in MaxEnt IRL (ablation)MaxEnt IRL · Objectworldruntime: \SI{8.08}{\hour} -> \SI{12.2}{\hour}Hurt
Use a single inner value-iteration step in MaxEnt IRL (ablation)MaxEnt IRL · ObjectworldEVD: 11.58 -> 4.33Improved
Add long-term keep-right and safety constraints to imitationDCIQL · SUMO German highway scenarioconstraint violations: 0Improved
Train on demonstrations with only 1000 samplesDCIQL · SUMO autonomous lane-changesdriving performanceImproved
Learn a reward through DCIQL rather than train CDQN on the true rewardSUMO autonomous lane-changes · SUMO highway scenariosperformanceImproved

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