AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning

Xin-Qiang Cai, Yao-Xiang Ding, Zixuan Chen, Yuan Jiang, Masashi Sugiyama, Zhi-Hua Zhou

ICLR 2023 · Reinforcement learning › Imitation learning · approach: Behavior cloning theory and models · 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
add importance weighting to GAILGAIL · Atari and MuJoCoreturnImproved
compare GAIL and IW with pi_1GAIL, IW · Atari and MuJoCoreturnNo clear effect
third-person IL under heterogeneous observationsTPIL · Hopper, Swimmer, Walker2dreturnHurt
GAMA mapping under support mismatchGAMA · Hopper and Walker2dreturnHurt
LBC with privileged O_E in AtariLBC · AtarireturnImproved
LBC when O_E is not more privileged than O_LLBC · most MuJoCo environmentsreturnHurt
use IWRE with rejection and limited queriesIWRE · 8 environmentsreturn: 6/8Improved
compare IWRE with PPO on true rewards under RAM inputPPO-RAM · Atari RAMreturnImproved
add random queries to GAIL (ablation)GAIL-Rand · Hopper, Swimmer, Walker2dreturnHurt
add random queries to IW (ablation)IW-Rand · Hopper, Reacher, Walker2dreturnImproved
increase query budget for TPIL (ablation)TPIL · Swimmer and Walker2dreturnMixed
increase query budget for IWRE (ablation)IWRE · MuJoCoreturnImproved

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