The central theme for research in this lab is autonomous agent learning. The agents are robots, models of robots, and interactive video game players. The learning is usually a form of evolutionary computation and almost always some type of computational intelligence. The agents are autonomous in the respect that they can operate on their own and the learning either takes place before operation or can happen during operation using learning systems that are offline from the agent. Most of the learning is for control programs, although some is for the morphology of the robot or control/morphology in combination.
Autonomous Agent Learning Lab
The Autonomous Agent Learning Lab at Connecticut College in New London, CT
- 17 followers
- United States of America
- joconno2@conncoll.edu
Pinned Loading
Repositories
Showing 10 of 20 repositories
- SCOPE-for-AtariSpaceInvaders Public archive
Evolving a game-playing agent for Atari Space Invaders via SCOPE.
ConnAALL/SCOPE-for-AtariSpaceInvaders’s past year of commit activity - SCOPE-for-Hexapod-Gait-Generation Public archive
SCOPE uses the Discrete Cosine Transform to compress high-dimensional pose data for hexapod control. By reducing input size from 2700 to 54, it enables faster and more effective evolutionary learning—achieving a 20% performance boost in gait generation.
ConnAALL/SCOPE-for-Hexapod-Gait-Generation’s past year of commit activity - core-niching Public
ConnAALL/core-niching’s past year of commit activity - image-gs Public Forked from NYU-ICL/image-gs
Official implementation of SIGGRAPH 2025 paper "Image-GS: Content-Adaptive Image Representation via 2D Gaussians"
ConnAALL/image-gs’s past year of commit activity - xpilot-ai Public
ConnAALL/xpilot-ai’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…