AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

A latent control model for realistic rodent motion

Aidan Sirbu, Charles Y Zhang, Yuanjia Yang, Bence Olveczky, Talmo Pereira, Blake Richards

NeurIPS 2026 · Reinforcement learning › Visual and representation RL · approach: Vision-based robot RL · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an embodied latent control model for generating realistic rodent motion in a virtual animal body, evaluated against imitation-trained baselines (abstract only; details not available).

Problem

Embodied models of animal behavior need to move like real animals to enable fair comparisons between biological and artificial agents; prior virtual rodent work trains realistic motion via imitation.

Approach

A latent control model for realistic rodent motion, building on prior virtual animal bodies and imitation-based motion training; specific mechanism not stated in the available abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add a behavior prior distilled from the frozen encoder, sampled instead of the motion prior (ablation)SCAMPER · random rollouts, Vendi scorebehavioral diversity (Vendi score)Improved
sample behavior prior instead of motion prior during random rollouts (ablation)SCAMPER · random rollouts, net displacement and arena occupancynet distance traveledImproved
sample behavior prior instead of motion prior during random rollouts (ablation)SCAMPER · random rolloutsKernel Inception Distance to training dataImproved
sample behavior prior instead of motion prior (ablation)SCAMPER · rearing height distributionWasserstein distance to training dataImproved
distill the behavior prior from the frozen encoder (ablation)SCAMPER · prior-encoder KLKL divergence (nats): 14.35 -> 5.88Improved
use the behavior prior for residual control instead of the motion prior (ablation)SCAMPER · residual control stabilitystability under residual controlHurt
residual control of motion prior instead of MIMIC-MJXSCAMPER · dense-reward locomotion speed trackingtarget speed matchingImproved
residual control of motion prior instead of training from scratchSCAMPER · gait analysis, all 18 metricsmean distance to real rat gait: walk 3.44 -> 0.59Improved
residual control of motion prior instead of MIMIC-MJX or scratchSCAMPER · dense-reward rearing tasktask success rateImproved
add behavior prior with learned gating to motion-prior-only variant (ablation)SCAMPER · sparse-reward arena foraging, large minimum spawn radiustreats collected per episodeImproved
add behavior prior on top of motion prior (ablation)SCAMPER · foraging with small spawn radiustreats collected per episodeNo clear effect
sampling the motion prior at very high noise (ablation)motion prior · random rolloutsdiversity vs realismMixed

Limitations

Experimental setup

Builds on: virtual rodent body (MuJoCo-based)

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