Dynamic Shaping: Acquiring Interfaces and Constructing Execution over Frozen Pretrained Components

We introduce Dynamic Shaping, a method for constructing executable neural arrangements through acquired response and partial-derivative interfaces over frozen pretrained components. The method learns local descriptions of available computation, ranks component rebindings using task-gradient alignment, transports the current interface across a rebinding, and retains changes through behavioral feedback. Continuous interface acquisition uses proximal policy optimization; the source coefficients remain fixed. We derive an exact identity relating transport error in component responses and partials to changes in action logits and their sensitivities. A pixels-only ViZDoom Basic study evaluates first task acquisition without a competent reference controller, demonstrations or intact response targets. Across three initializations and 100 shared held-out game seeds, initial arrangements succeed on 86/300 controller/episode pairs; joint interface-and-binding construction succeeds on 295/300. Fixed-binding interface acquisition also reaches 295/300. Each policy executes four source fragments, with 110 acquired interface values and fixed random visual and action projections. The artifact includes all candidate trials, interventions and costs; all 1,200 recorded initial/retained outcomes replay exactly. The contribution is an explicit profile, rebind, transport and retain procedure and a reproducible reference-free acquisition case over frozen pretrained computation.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20573
Primary Topic
Reinforcement Learning in Robotics
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Dynamic Shaping: Acquiring Interfaces and Constructing Execution over Frozen Pretrained Components

Nathaniel Oh
arXiv (Cornell University)
Reinforcement Learning in Robotics
preprint

Dynamic Shaping: Acquiring Interfaces and Constructing Execution over Frozen Pretrained Components

Nathaniel Oh
preprint en

Abstract

We introduce Dynamic Shaping, a method for constructing executable neural arrangements through acquired response and partial-derivative interfaces over frozen pretrained components. The method learns local descriptions of available computation, ranks component rebindings using task-gradient alignment, transports the current interface across a rebinding, and retains changes through behavioral feedback. Continuous interface acquisition uses proximal policy optimization; the source coefficients remain fixed. We derive an exact identity relating transport error in component responses and partials to changes in action logits and their sensitivities. A pixels-only ViZDoom Basic study evaluates first task acquisition without a competent reference controller, demonstrations or intact response targets. Across three initializations and 100 shared held-out game seeds, initial arrangements succeed on 86/300 controller/episode pairs; joint interface-and-binding construction succeeds on 295/300. Fixed-binding interface acquisition also reaches 295/300. Each policy executes four source fragments, with 110 acquired interface values and fixed random visual and action projections. The artifact includes all candidate trials, interventions and costs; all 1,200 recorded initial/retained outcomes replay exactly. The contribution is an explicit profile, rebind, transport and retain procedure and a reproducible reference-free acquisition case over frozen pretrained computation.

arXiv (Cornell University)
Reinforcement Learning in Robotics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon