AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models

Pranaya Jajoo, Harshit Sikchi, Siddhant Agarwal, Amy Zhang, Scott Niekum, Martha White

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Latent-space world models · 1 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 orthogonality regularization (lambda>0) to latent dynamics prediction (ablation)RLDP · zero-shot RL (DMC)average returnImproved
add spherical normalization on predicted latent next state g (ablation)RLDP · Quadruped (DMC)average return: 514.02 -> 612.77Improved
add spherical normalization on g (ablation)RLDP · Pointmass (DMC)average return: 581.63 -> 671.11Improved
add spherical normalization on g (ablation)RLDP · Quadruped Walk (DMC)return: 465.40 vs 519.39 without SNHurt
learned representations (FB, PSM, RLDP) instead of random features (ablation)zero-shot BFM · ExoRL DMCreturn: e.g. Walker Stand 392.40 -> 890.40Improved
RLDP vs FB and PSM in offline DMC zero-shotRLDP · ExoRL DMC (Walker, Cheetah, Quadruped, Pointmass)return: Walker Flip 977.08 (FB) vs 492.94; Quadruped Jump 549.57 (PSM) vs 733.32Mixed
RLDP representations in low-coverage D4RLRLDP · D4RL (6 tasks)normalized return: outperforms all baselines in 5 of 6 tasksImproved
explicit Bellman backups in representation learning (ablation)RLDP · low-coverage D4RLpolicy performanceHurt
RLDP on SMPL Humanoid (45 tasks)RLDP · SMPL Humanoidnormalized returnNo 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