I was able to get an AOgmaNeo agent to play Atari Pong on a Teensy 4.1 microcontroller. I believe it is the most resource-efficient general-purpose reinforcement learner!
Member since
November 10, 2020
Recent Activity
A robotic demo of my project here (AOgmaNeo, from-scratch AI system): https://www.youtube.com/watch?v=JrCU5My2L6I
New blog post:
Findings about Unsupervised Behavioral Learning (UBL)
New blog post:
New release 1.5.0 + a possible paradigm shift?
New blog post:
The Return of Topology + Experiments with Fast Weights
New blog post:
UBL demo + collab!
New blog post:
"GAN Theft Auto" but with AOgmaNeo
New blog post:
Dual Encoder Setup
New blog post:
More Error-Driven Encoders and Decoders + Upcoming Demos
New blog post:
ESR-light and conservative Q-learning
New blog post:
Demo Work and Topology
While experimenting with new encoders (particularly ones based on ART - adpative resonance theory), I also ran some experiments with AOgmaNeo where an agent must find a red box. Since AOgmaNeo builds a world model during this reinforcement learning process, I can actually see "dreams" of what it has modeled in the world.