AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Data augmentation for efficient learning from parametric experts

Alexandre Galashov, Josh Merel, Nicolas Heess

NeurIPS 2022 · Reinforcement learning › Imitation learning · approach: Offline imitation from imperfect data · 1 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
Add expert re-querying of actions at perturbed states (APC) instead of keeping the original action (Naive ABC) (ablation)Behavioral cloning · Offline cloning on Humanoid Run, Humanoid Walls, Insert Pegepisodic reward vs number of trajectoriesImproved
Add state perturbation with the same action (Naive ABC) to plain BC (ablation)Behavioral cloning · Offline cloning on all tasksepisodic rewardNo clear effect
Shrink the student network torso below [256, 256, 256] (expert compression) (ablation)APC vs BC · Expert compressionepisodic rewardMixed
Add APC to cloning from a privileged expert with vision-based student (ablation)Behavioral cloning · Insert Peg with privileged target position vs visionepisodic rewardImproved
Use short trajectories (200 steps) plus one full trajectory instead of full trajectories (ablation)BC and Naive ABC · Humanoid Run and Humanoid Wallsepisodic rewardHurt
Use short trajectories (200 steps) instead of full trajectories (ablation)BC and Naive ABC · Insert Pegepisodic rewardImproved
Use short trajectories instead of full ones (ablation)APC · All three tasksepisodic rewardNo clear effect
Add APC state-based augmentation to DAgger (beta 0 and 0.3) (ablation)DAgger · Humanoid Run and Wallsepisodic rewardImproved
Add image random-crop augmentation to DAgger (ablation)DAgger on Humanoid Walls · Humanoid Wallsepisodic rewardImproved
Use analytical cross-entropy instead of log-probability of expert mean action (ablation)DAgger · Humanoid Run and Wallsepisodic rewardImproved
Add APC to kickstarting (ablation)Kickstarting · Humanoid Runepisodic rewardImproved
Add APC to kickstarting (ablation)Kickstarting · Humanoid Wallsepisodic rewardNo clear effect

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