Tyna <> AI
Tyna <> AI
Home
Learning Posts
Final Project
Publications
Contact
Light
Dark
Automatic
Tyna Eloundou
Member of Technical Staff
OpenAI
About Me
Current Role: Member of Technical Staff @ OpenAI
Interests
Artificial Intelligence
Reinforcement Learning
Decision Theory
Mechanism Design
Distributed Systems
Learning Posts
Multiple Experts, Multiple Objectives
At long last, I present my Scholars project, where I engineered a (somewhat primitive) framework that disentangles data containing many behaviors from different experts to learn to steer a model towards one mode of behavior or another.
Last updated on Jul 10, 2021
15 min read
The Final Stretch
As I round the corner of the final days of my project, I am striving to succeed in provably demonstrating its practical utility, simplicity and contributions. The neural architecture I have designed so far, however, is anything but simple.
Last updated on Mar 16, 2021
1 min read
Exploring New Depths
Over the last two weeks I have been delving into new depths, turning a problem over in my mind for days at a time, without certainty of success. Continuing to probe at an idea in the face of possible failure can be daunting, and I wanted to share some of the tips that helped me overcome the challenges of designing novel solutions.
Last updated on Mar 2, 2021
3 min read
The Makings of an Option
Reinforcement learning literature involves learning to pursue actions that provide sufficient enough rewards (or minimize the agent’s cost). As we have previously seen, encouraging continuous actions defined as an “environment step” can be tricky because of the credit assignment problem, wherein the learning function must attribute credit for rewards or costs to some actions taken along a trajectory**.
Last updated on Feb 16, 2021
5 min read
Making and Benchmarking a Clone
The Expert We trained multiple experts at different thresholds and constraints, but in this report we will discuss a configuration set (alias Marigold), for which we ran multiple smaller cloning experiments.
Last updated on Feb 1, 2021
3 min read
See all posts
Projects
Popular Topics
ai
Cite
×