ARC (Abstraction and Reasoning Corpus)
ARC (Abstraction and Reasoning Corpus) is a dataset jointly created by Gwangju Institute of Science and Technology and Korea University, intended to evaluate and improve AI systems' abstract reasoning capabilities. It contains various complex grid‑editing tasks with large action spaces and diverse task types. The dataset was generated using the Gymnasium environment by defining specific action and state spaces to simulate ARC challenges. ARC is primarily used in reinforcement learning to develop and test AI models capable of solving complex reasoning problems.
Description
ARCLE - ARC Learning Environment
Overview
ARCLE is a reinforcement‑learning environment for training Abstraction and Reasoning Corpus and similar datasets, built on Farama’s Gymnasium.
Environments
ARCLE includes the following environments:
RawARCEnv: Environment that only supports coloring, resizing answer grid, and submission actions.ARCEnv: Implements ARC’s browser‑test interface, supporting coloring, flood‑fill, copy, and paste operations.O2ARCv2Env: Implements the O2ARCv2 interface, extendingARCEnvwith move, rotate, flip, crop, etc.
Version History
0.2.6
- Environment changes:
O2ARCv2Envnow accessible viaO2ARCEnvorO2ARCEnv‑v2.- Unified observation type to
np.int8. - Unified observation space to
BoxorMultiBinarydict for proper flattening. - Removed over‑strict constraints from
AbstractARCEnv; users only need to overridecreate_operations.
- Added action wrappers (
BBoxWrapper,PointWrapper) to switch selection mode. Loadernow supports configurable RNG.- Organized examples.
- Fixed
terminatednot being emitted whenmax_trialis infinite (-1).
0.2.5
- Python 3.8 support.
- Environment changes:
- Renamed
ARCEnvtoRawARCEnv. - Removed
MiniARCEnv; useRawARCEnvwithloader=MiniARCLoader(). - Added new
ARCEnvwith action space matching ARC test interface. - All environments fully observable; state‑related variables now in
current_statedict. - Added n‑trial mode via
gym.make(); -1 denotes unlimited trials. - Customizable
Submitaction.
- Renamed
- Fixed boundary issues for flood‑fill, paste, copy.
0.2.2
- Fixed issue where total reward (all‑or‑nothing) was only given on submission.
0.2.1
O2ARCv2Env‑v0:- Changed
ResizeGridtoCropGrid. - Enforced
FloodFillto select a single pixel. - Treated black pixels as background for
CopyI,CopyO,Paste. action[selection]now accepts integers.
- Changed
0.2.0
- Renamed
ArcEnv‑v0andMiniArcEnv‑v0toARCEnv‑v0andMiniArcEnv‑v0. - Added
O2ARCv2Env‑v0. - Added O2ARC actions:
- Uses
selectionandselected. - Supports coloring, flood‑fill, move, rotate, flip, copy, paste, clipboard.
- Uses
0.1.1
- Updated imagery.
- Fixed minor bugs.
0.1.0
- Initial build.
- Released
ArcEnv‑v0andMiniArcEnv‑v0.
AI studio
Generate PPTs instantly with Nano Banana Pro.
Generate PPT NowAccess Dataset
Please login to view download links and access full dataset details.
Topics
Source
Organization: arXiv
Created: 7/30/2024
Power Your Data Analysis with Premium AI Models
Supporting GPT-5, Claude-4, DeepSeek v3, Gemini and more.
Enjoy a free trial and save 20%+ compared to official pricing.