AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Efficient and Safe Molecular Assembly via Reinforcement Learning and Constraint Solving

Stefan Pranger, Bernhard Ramsauer, Oliver T. Hofmann, Bettina Könighofer

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer

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 CrossQ or TQC instead of PPORL agent · Cross-shaped molecule sigma 0.025Iaverage movement (nm): 0.49 -> 0.77Improved
use CrossQ instead of TQCRL agent · Cross-shaped molecule sigma 0.1I (w=6 nm)average movement (nm): 0.66 -> 0.8Improved
use PPORL agent · Cross-shaped molecule sigma 0.1Icorridor confinementHurt
use TQC instead of CrossQ/PPORL agent · Circular moleculeaverage movement (nm): 0.80 -> 0.83Improved
widen corridor from 4 nm to 6 nmCrossQ and TQC · Cross-shaped molecule sigma 0.1Icorridor confinement (%): 95 -> 98.7Improved
use honeycomb instead of square assembly layoutSMT scheduling · Construction planningnumber of iterationsHurt
add obstacles to the surfaceconstruction planning · Construction planningcomputation timeHurt
increase assembly sizeconstruction planning · Construction planningiterations and timeHurt
increase molecular position noise from sigma 0.025I to 0.1Ifull framework · Full assembly constructioncorridor confinement (%): 99.8 -> 97.3Hurt

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