AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

CEIL: Generalized Contextual Imitation Learning

Jinxin Liu, Li He, Yachen Kang, Zifeng Zhuang, Donglin Wang, Huazhe Xu

NeurIPS 2023 · Reinforcement learning › Imitation learning · approach: Offline imitation from imperfect data · 2 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 CEIL instead of the strongest listed baselineOffline single-domain LfD · D4RL medium/medium-replay/medium-expert, 4 environmentssum of normalized scores: 754.6 -> 1163.5Improved
Use CEIL instead of the strongest listed baselineOffline single-domain LfO · D4RL medium/medium-replay/medium-expert, 4 environmentssum of normalized scores: 741.7 -> 821.7Improved
Use CEIL instead of the strongest listed baselineOffline cross-domain LfD · D4RL medium/medium-replay/medium-expert, 4 environmentssum of normalized scores: 749.7 -> 780.9Improved
Use CEIL instead of the strongest listed baselineOffline cross-domain LfO · D4RL medium/medium-replay/medium-expert, 4 environmentssum of normalized scores: 724.4 -> 727.3Improved
Add expert-matching optimization of the hindsight embedding function f_phi (ablation)CEIL · S-off-LfD, D4RL medium/medium-replay/medium-expertsum of normalized scores: 1030.8 -> 1163.5Improved
Add the J_MI latent-space expert-matching objective (ablation)CEIL · S-off-LfD, D4RL medium/medium-replay/medium-expertsum of normalized scores: 951.4 -> 1163.5Improved
Add expert-matching optimization of the hindsight embedding function f_phi (ablation)CEIL · S-off-LfO, D4RL medium/medium-replay/medium-expertsum of normalized scores: 759.2 -> 821.7Improved
Add the J_MI latent-space expert-matching objective (ablation)CEIL · S-off-LfO, D4RL medium/medium-replay/medium-expertsum of normalized scores: 792.0 -> 821.7Improved
Add cross-domain regularization that encourages task-relevant embeddings (ablation)CEIL · Cross-domain offline ILnormalized scoreImproved
Add expert observations and cross-domain expert behaviors to the offline training dataCEIL · Hybrid offline IL, Hopper-v2normalized score: 29.4 -> 58.6Improved
Use CEIL for online learning from observationsCEIL · Online LfO, Walker2d-v2returnHurt

Later papers that compared with this method

1 later accepted paper reports CEIL as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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