Repository
Research
actionabi · Archerkattri
ActionABI studies recovery of undocumented robot action-tensor semantics from trajectories.
Visualization & data tools
Benchmarks / Research
actionshift · Archerkattri
ActionShift evaluates adaptation to hidden robot action-interface contracts on ManiSkill tasks.
Overview
ActionShift evaluates adaptation to hidden robot action-interface contracts on ManiSkill tasks.
Publisher summary: “Benchmark for adaptation to hidden robot action-interface contracts: 4 ManiSkill tasks, preregistered gates, belief/probe/learned methods, delay-aware control. Same policy, different wiring — can it…”
Use its repository to inspect the implementation, documentation and supported workflows. This directory record identifies the maintainer, code license and related resources; it does not claim that the project has been installed or tested on your robot.
Project information
- Maintainer
- Archerkattri
- Primary language
- Python
- Repository code license
- MIT
- Model-weight license
- Not recorded
- Dataset license
- Not recorded
- Hardware design license
- Not recorded
- Maintenance
- Not archived in the last recorded metadata
- Last observed repository push
- 2026-09-19
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Documentation sections
- ActionShift
- Part of the Action-Interface pair
- Contents
- What is this?
- Who is this for?
- How it works
Browse this resource’s categories
Explore related collections
Browse Benchmarks →More in Benchmarks
Repository
Research