Posts by Tags

ablation

Can Dueling DQN Stabilize Self-Improving Code? A Colab Experiment

6 minute read

Published:

I tested an idea from reinforcement learning against a small, real program-optimization loop: can a slowly updated critic help a system choose better improvements to its own code? The answer is less conclusive than the best-looking bar chart.

agents

category1

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

category2

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

code-optimization

Can Dueling DQN Stabilize Self-Improving Code? A Colab Experiment

6 minute read

Published:

I tested an idea from reinforcement learning against a small, real program-optimization loop: can a slowly updated critic help a system choose better improvements to its own code? The answer is less conclusive than the best-looking bar chart.

cool posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

evaluations

recursive-self-improvement

Can Dueling DQN Stabilize Self-Improving Code? A Colab Experiment

6 minute read

Published:

I tested an idea from reinforcement learning against a small, real program-optimization loop: can a slowly updated critic help a system choose better improvements to its own code? The answer is less conclusive than the best-looking bar chart.

reinforcement-learning

Can Dueling DQN Stabilize Self-Improving Code? A Colab Experiment

6 minute read

Published:

I tested an idea from reinforcement learning against a small, real program-optimization loop: can a slowly updated critic help a system choose better improvements to its own code? The answer is less conclusive than the best-looking bar chart.

research-engineering

Can Dueling DQN Stabilize Self-Improving Code? A Colab Experiment

6 minute read

Published:

I tested an idea from reinforcement learning against a small, real program-optimization loop: can a slowly updated critic help a system choose better improvements to its own code? The answer is less conclusive than the best-looking bar chart.

safety

self-improvement