Subnode [[@flancian/reinforce]] in node [[reinforce]]
from garden/flancian/reinforce.md by @flancian
from garden/flancian/reinforce.md by @flancian
Reinforce
- In machine learning, a crucial step in training and improving models, particularly when using [[reinforcement learning]].
- This [[agora]] is built under the assumption that a [[social distributed knowledge graph]] is a worthy platform to build a variety of pro-social internet tools, and train a variety of generally socially beneficial models -- that a community of users could agree to [[train]] and [[improve]].