AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Imitation Learning from Imperfection: Theoretical Justifications and Algorithms

Ziniu Li, Tian Xu, Zeyu Qin, Yang Yu, Zhi-Quan Luo

NeurIPS 2023 · Reinforcement learning › Imitation learning · approach: Offline imitation from imperfect data · 3 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 ISW-BC instead of BC (add reweighted supplementary data)BC · MuJoCo, Noisy Expert, avg normalizednormalized score: 38% -> 69%Improved
Add supplementary data naively (NBCU) vs BC under large shiftBC · MuJoCo, Noisy Expert, avg normalizednormalized score: 38% -> 35%Hurt
Add supplementary data naively (NBCU) vs BC under small shiftBC · MuJoCo, Full Replay, avg normalizednormalized score: 38% -> 92%Improved
ISW-BC instead of NBCU under large shiftNBCU · MuJoCo, Noisy Expert, avg normalizednormalized score: 35% -> 69%Improved
ISW-BC instead of NBCU under small shiftNBCU · MuJoCo, Full Replay, avg normalizednormalized score: 92% -> 94%No clear effect
ISW-BC instead of DWBC under small shiftDWBC · MuJoCo, Full Replay, avg normalizednormalized score: 44% -> 94%Improved
ISW-BC instead of DemoDICE under large shiftDemoDICE · MuJoCo, Noisy Expert, avg normalizednormalized score: 49% -> 69%Improved
ISW-BC instead of DWBC under large shiftDWBC · MuJoCo, Noisy Expert, avg normalizednormalized score: 62% -> 69%Improved
Use ISW-BC instead of BC on Atari with noisy supplementary dataBC · Atari, Noisy Expert, avg normalizednormalized score: 32% -> 36%Improved
NBCU instead of BC on Atari with noisy supplementary dataBC · Atari, Noisy Expert, avg normalizednormalized score: 32% -> 27%Hurt
NBCU instead of BC on Atari with full replayBC · Atari, Full Replay, avg normalizednormalized score: 32% -> 50%Improved
ISW-BC instead of NBCU on Atari full replayNBCU · Atari, Full Replay, avg normalizednormalized score: 50% -> 50%No clear effect

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