AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Strictly Batch Imitation Learning by Energy-based Distribution Matching

Daniel Jarrett, Ioana Bica, Mihaela van der Schaar

NeurIPS 2020 · Reinforcement learning › Imitation learning · approach: Offline imitation from imperfect data · 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
Add the energy-based occupancy loss to behavioral cloningEDM · Acrobot-v1, CartPole-v1, LunarLander-v2, BeamRider-v4 (1 demo)average return: Acrobot-v1: 0.796 -> 0.896; CartPole-v1: 0.321 -> 0.428; LunarLander-v2: 0.575 -> 0.633; BeamRider-v4: 0.124 -> 0.486Improved
Add the energy-based occupancy loss to behavioral cloningEDM · MIMIC-III-2aACC: 0.861 -> 0.891Improved
Add the energy-based occupancy loss to behavioral cloningEDM · MIMIC-III-4aACC: 0.696 -> 0.720Improved
Use EDM rather than the strongest baseline at 15 demosEDM · CartPole-v1average return: 0.998 ± 0.001 vs. 0.998 ± 0.002No clear effect
Use EDM rather than the strongest baseline at 15 demosEDM · LunarLander-v2average return: 0.970 ± 0.028 vs. 0.970 ± 0.033No clear effect
Use EDM rather than the strongest baselineEDM · MIMIC-III-2a and MIMIC-III-4aAUC: MIMIC-III-2a: 0.915 -> 0.922; MIMIC-III-4a: 0.864 -> 0.873Improved
Use an off-policy adaptation that predicts next-state feature mapsDSFN · Gym environmentsaverage returnHurt

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