Jonathan Ho
6 posts
Evolved Policy Gradients
Learning a Hierarchy
Faster Physics in Python
Robots that Learn
We've created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
We've discovered that evolution strategies (ES), an optimization technique that's been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks, while overcoming many of RL's inconveniences.
Generative Models
This post describes four projects that share a common theme of enhancing or using generative models, a branch of unsupervised learning techniques in machine learning.