AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Coherent Soft Imitation Learning

Joe Watson, Sandy Huang, Nicolas Heess

NeurIPS 2023 · Reinforcement learning › Imitation learning · approach: Reward learning from demonstrations · 0 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 CSIL instead of the strongest listed baseline (GAIL)Tabular inverse optimal control · Dense Nominalnormalized performance: 0.251 -> 0.257Improved
Use CSIL instead of the strongest listed baseline (GAIL)Tabular inverse optimal control · Dense Windynormalized performance: 0.111 -> 0.107Hurt
Use CSIL instead of the strongest baselinesTabular inverse optimal control · Sparse Nominalnormalized performance: 1.237 -> 1.237No clear effect
Use CSIL instead of the strongest listed baseline (Classifier)Tabular inverse optimal control · Sparse Windynormalized performance: 0.044 -> 0.044No clear effect
Pretrain IQLearn or PPIL with behavioral cloning before imitation learning (ablation)IQLearn and PPIL · Online continuous controlepisode returnMixed
Use negative CSIL rewards rather than positive CSIL rewards (ablation)CSIL on robomimic tasks · Online human demonstrationssuccess rateImproved
Use the negative CSIL reward rather than a constant negative reward (ablation)CSIL on robomimic tasks · Online human demonstrations, fewer demonstrationssuccess rateImproved
Use a faithful heteroscedastic regression loss instead of NLLH (ablation)Heteroscedastic regression policies · Regression toy problemmean prediction errorImproved
Use a faithful heteroscedastic regression loss instead of NLLH (ablation)Heteroscedastic regression policies · Regression toy problemuncertainty quantificationNo clear effect
Regularize finetuning against the cloned policy instead of using the uniform prior (ablation)CSIL · Continuous controlpolicy stabilityImproved
Refine the coherent reward using additional replay data (ablation)CSIL · Continuous control, especially fewer demonstrationsdownstream performanceImproved
Use an unrefined reward rather than minimax-refining the coherent reward (ablation)CSIL · Continuous controllearning stabilityHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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