Actor Critic Algorithms
Learning actor critic algorithms
Finlay Miller
Master's student at Dalhousie University under Sageev Oore working on music and interactive AI.
AI and Software Engineering at Vigilant AI working on document data extraction, both structured and unstructured, using LLMs and small, local models.
I use this site to collect personal projects, experiments, and notes from self-directed study in machine learning and music technology.
Recent wWriting
Policy Gradients
Exploring policy gradients
Introduction to Deep Reinforcement Learning
Introduction to reinforcement learning terms and concepts
Supervised Learning
Introduction to supervised learning terms and concepts
Introduction
I'm following along with Berkeley's Deep Reinforcement Learning Course