We're exploring related ideas in embodied AI rather than LLM agents. MH-FLOCKE uses Izhikevich spiking neurons with R-STDP to control quadruped locomotion — the memory is in the synaptic weights, not in a vector store.
The brain persists across sessions: stop the robot, restart it, synaptic weights reload and it continues from where it left off. Decay happens naturally through R-STDP — synapses that don't contribute to reward weaken over time. No explicit forgetting mechanism needed.
Currently running on a Unitree Go2 (MuJoCo) and a 100€ Freenove robot dog (Raspberry Pi 4, real hardware). Same architecture, different bodies.
Interesting parallel to spiking neural networks — they're essentially 1-bit communication (spike or no spike) with analog membrane potentials. We use 5k Izhikevich neurons for quadruped locomotion control and they beat PPO at the same sample budget. The efficiency argument for 1-bit goes beyond LLMs.
The scratchpad.md for agent working memory is a nice touch. Having a persistent record of what was tried and why matters more than most people realize when debugging automated experiment loops.
The endorsement system is a real barrier for independent researchers. I've been trying to get endorsed for cs.NE for weeks — the work is published on aiXiv with video results, but without an institutional email or personal connection to an existing author, you're stuck. Glad to see arXiv thinking about independence — hope they also rethink access for non-institutional researchers.
The brain persists across sessions: stop the robot, restart it, synaptic weights reload and it continues from where it left off. Decay happens naturally through R-STDP — synapses that don't contribute to reward weaken over time. No explicit forgetting mechanism needed.
Currently running on a Unitree Go2 (MuJoCo) and a 100€ Freenove robot dog (Raspberry Pi 4, real hardware). Same architecture, different bodies.
github.com/MarcHesse/mhflocke