AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Time

Vinicius G. Goecks, Gregory M. Gremillion, Vernon J. Lawhern, John Valasek, Nicholas R. Waytowich

AAAI 2019 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Human-AI coordination agents · 39 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
Combine demonstrations followed by interventions rather than using demonstrations aloneCycle-of-Learning · AirSim perching, 20 interactionstask completion: 76.25% (± 2.72% std. error) -> 90.25% (± 5.63% std. error)Improved
Combine demonstrations followed by interventions rather than using demonstrations aloneCycle-of-Learning · AirSim perching, 8 interactionstask completion: 54.00% (± 8.95% std. error) -> 74.75% (± 9.38% std. error)Improved
Use demonstrations followed by interventions instead of demonstrations aloneCycle-of-Learning · AirSim perching, averaged over presented conditions and datasetstask completion: +12.81% (± 3.61% std. error)Improved
Use demonstrations followed by interventions instead of demonstrations aloneCycle-of-Learning · AirSim perching, averaged over presented conditions and datasetshuman-provided samples: 32.05% (± 3.25% std. error) less human samplesImproved
Use demonstrations followed by interventions instead of demonstrations aloneCycle-of-Learning · AirSim perching, 20 interactionshuman-provided samples: 37.79% fewer data samplesImproved
Use interventions only instead of demonstrations followed by interventionsCycle-of-Learning · AirSim perching, 8, 12, and 20 interactionstask completionHurt
Use PPO with 2 actions and fixed downward throttle instead of the full action spacePPO · AirSim perching, 500 episodestask completion: 100%Improved
Increase PPO action dimensions from 2 to 3, requiring throttle controlPPO · AirSim perching, 1000 episodestask completion: 100% -> less than 5%Hurt

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