AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Optimistic Task Inference for Behavior Foundation Models

Thomas Rupf, Marco Bagatella, Marin Vlastelica, Andreas Krause

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Inferring decision-making from behavior · 5 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
update the task embedding every step instead of once per episode (ablation)OpTI-BFM · DMC (Walker, Cheetah, Quadruped)relative performance: episode-level updates lead to slower improvement than changing every stepImproved
use the optimistic criterion instead of Thompson sampling (ablation)OpTI-BFM · DMC Cheetahepisodic return: significant gap between OpTI-BFM and its TS variant in CheetahImproved
use linear-structure-aware OpTI-BFM instead of black-box policy search LoLAonline task inference · DMCepisodic return: LoLA makes slower progressImproved
collect data actively (OpTI-BFM, RND) instead of passive Random rolloutstask inference data source · DMCrelative performance of inferred policyImproved
collect task-aware data (OpTI-BFM) instead of task-agnostic RND explorationtask inference data source · DMCrelative performance of inferred policyImproved
reduce decay rate rho below 1.0 for old observations (ablation)OpTI-BFM · DMC Walker speedup/slowdown (non-stationary)velocity tracking: rho=1.0 struggles to adapt; reduced rho tracks target more accuratelyImproved
make decay rate rho too small (ablation)OpTI-BFM · DMC Walker speedup/slowdown (non-stationary)velocity trackingHurt
warm-start with n i.i.d. labeled states (ablation)OpTI-BFM · DMC Cheetahreturn: initial performance increases quickly as n growsImproved

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