AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Learning from Interventions Using Hierarchical Policies for Safe Learning

Jing Bi, Vikas Dhiman, Tianyou Xiao, Chenliang Xu

AAAI 2020 · Reinforcement learning › Imitation learning · approach: Behavior cloning theory and models · 7 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 hierarchical sub-goal policies instead of a direct Branched policyLfI in CARLA · CARLA urban drivingtime and distance without interventionImproved
Add Backtracking to interpolate actions around an expert interventionLfI in CARLA · CARLA urban drivingtime and distance without interventionImproved
Combine hierarchical sub-goal policies with BacktrackingLfI in CARLA · CARLA urban drivingtime and distance without interventionImproved
Use sub-goals with LbB rather than Branched+DemoLfI in CARLA · CARLA urban drivingtraining data samples per iterationImproved
Increase the future sub-goal horizon from a small value toward k=5 (ablation)Sub-goal+LbB · CARLA urban drivingtime and distance without interventionImproved
Increase the future sub-goal horizon beyond k=5 (ablation)Sub-goal+LbB · CARLA urban drivingtime and distance without interventionHurt
Use Branched rather than Sub-goal policy representation (ablation)LfI in CARLA · CARLA urban drivingtime and distance without interventionHurt
Use Demo rather than LbB data collection (ablation)LfI in CARLA · CARLA urban drivingtraining data samples per iterationHurt

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