AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition

Justin Fu, Avi Singh, Dibya Ghosh, Larry Yang, Sergey Levine

NeurIPS 2018 · Reinforcement learning › Imitation learning · approach: Reward learning from demonstrations · 53 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 the ANY query instead of ALLEvent-based control · HalfCheetahMin. Dist: 2.01 (0.48) -> 0.97 (0.46)Improved
Use the ALL query instead of ANYEvent-based control · HalfCheetahAvg. Dist: 1.35 (0.20) -> 1.33 (0.16)No clear effect
Use the ANY query instead of ALLEvent-based control · LobberMin. Dist: 0.36 (0.21) -> 0.25 (0.20)Improved
Use VICE-ALL event learning instead of the offline classifierVICE · MazeFinal distance to goal: 0.35 (0.29) -> 0.20 (0.19)Improved
Use VICE-ANY event learning instead of the offline classifierVICE · MazeFinal distance to goal: 0.37 (0.21) -> 0.23 (0.15)Improved
Use VICE-ALL event learning instead of the offline classifierVICE · AntFinal distance to goal: 2.71 (0.75) -> 0.64 (0.32)Improved
Use VICE-ANY event learning instead of the offline classifierVICE · AntFinal distance to goal: 3.93 (1.56) -> 0.62 (0.55)Improved
Use VICE-ALL event learning instead of the offline classifierVICE · PusherFinal distance to goal: 0.25 (0.01) -> 0.09 (0.01)Improved
Use VICE-ANY event learning instead of the offline classifierVICE · PusherFinal distance to goal: 0.25 (0.01) -> 0.11 (0.01)Improved
Use VICE-ALL instead of true binary event indicatorsVICE · AntFinal distance to goal: 1.61 (1.35) -> 0.64 (0.32)Improved
Use VICE-ANY instead of true binary event indicatorsVICE · AntFinal distance to goal: 1.61 (1.35) -> 0.62 (0.55)Improved
Use VICE-ALL instead of true binary event indicatorsVICE · PusherFinal distance to goal: 0.17 (0.03) -> 0.09 (0.01)Improved

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