AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Curriculum Offline Imitating Learning

Minghuan Liu, Hanye Zhao, Zhengyu Yang, Jian Shen, Weinan Zhang, Li Zhao, Tie-Yan Liu

NeurIPS 2021 · Reinforcement learning › Imitation learning · approach: Imitation combined with RL · 5 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 adaptive neighboring-policy imitation with a return filter instead of direct behavior cloningOffline imitation on final datasets · hopper-finalreturn: 1480.4 (800.2) -> 2872.5 (133.9)Improved
Use COIL rather than the strongest listed baselineOffline learning · halfcheetah-finalreturn: 10882.0 (1042.7) -> 9328.5 (1940.6)Hurt
Use COIL rather than the strongest listed baselineOffline learning · hopper-mediumreturn: 2557.3 -> 3012.0 (332.2)Improved
Use COIL rather than the strongest listed baselineOffline learning · hopper-medium-replayreturn: 3009.6 -> 1333.7 (271.1)Hurt
Use COIL rather than the strongest listed baselineOffline learning · halfcheetah-medium-expertreturn: 9470.3 (4178.9) -> 10535.6 (3334.9)Improved
Use a larger selected-trajectory count N on halfcheetah-medium-expert (ablation)COIL · halfcheetah-medium-expertreturnImproved
Use a medium selected-trajectory count N (4 or 5) instead of a larger batch (ablation)COIL · halfcheetah-finalreturnImproved
Remove the return filter (alpha=1.0) (ablation)COIL · hopper-finalreturnHurt
Remove moving-average smoothing from the return filter (alpha=0.0) (ablation)COIL · hopper-finalreturnHurt
Use rapid moving-average filtering (alpha=0.5) (ablation)COIL · hopper-finalreturnHurt
Replace policy-distance-based curriculum with return-ordered BC (ablation)COIL · final datasetsreturnHurt
Replace policy-distance-based curriculum with buffer-shrinking BC (ablation)COIL · final datasetsreturnHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

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