AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Intention-Conditioned Flow Occupancy Models

Chongyi Zheng, Seohong Park, Sergey Levine, Benjamin Eysenbach

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL · 8 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 implicit GPI (upper expectile) instead of standard GPI over finite intentions (ablation)InFOM · quadruped jump and scene task 1return / success rate: 44% more performant, 8x smaller varianceImproved
add the variational intention encoder (vs FOM with one-step policy improvement) (ablation)InFOM · quadruped jump and scene task 1return / success rateImproved
use variational intention encoder instead of HILP or FB representations for FOM conditioning (ablation)flow occupancy models · OGBench cube double task 1 and othersdownstream performance: better on 3 of 4 tasksImproved
pre-train InFOM and fine-tune vs alternative pre-training methodsInFOM · OGBench state-based manipulationsuccess rate: +36% over best baselineImproved
InFOM on image inputsInFOM · OGBench visual taskssuccess rate: +31% over best baselineImproved
InFOM vs baselines on easier ExORL domainsInFOM · ExORL cheetah and quadrupedreturnNo 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