I don’t think it’s working quite yet, but maybe next time?
Author: Ted
SOFT actor-critic reinforcement
And also a python package called Tianshou.
What’s up with Ted?
Howdy! My name is Ted, I’m a squid, I write stuff sometimes.
I don’t post enough on this website, so I wanted to share what’s goin’ on in my life right now. It’s good, it’s bad, it’s ugly.
The good? I was accepted as a PhD student at the Okinawa Institute of Science and Technology! Wow! A few years ago I studied abroad in Tokyo, and now I’m excited to study in Okinawa too.
The bad? Given the ongoing pandemic, it might be a while before I can get a student-visa to Japan! I’ve already been double-vaccinated with Pfizer, and I’ve agreed to be tested and quarantined anyway, but no student-visas! The LA embassy told me to call back in a few weeks.
The ugly? Two years ago my dad died, a year ago my uncle committed suicide, and my grandfather’s mental health isn’t looking well. So there’s a lot on my mind.
Anyway, I’ll try posting more on this site more. I think that’ll be a decent amount of socialization!
Slender Man vs the Dalai Lama: What’s a tulpa?
I gotta listen to more Monster Talk, I like these folks!
Actor-Critic reinforcement learning
Gotta reinforce this learning! Now I’m learning the actor-critic method.
Phantom limbs, non-limb phantoms
This episode has nothing to do with Venture Bros, but you should watch that too, haha.
I taught my computer to play PONG with reinforcement learning!
It’s pretty good at PONG, too! Whoo!
Happy Father’s Day!
This week’s talking-squid video-essay is about stuff I watched about dads, WITH my dad!
This week’s talking-squid video-essay is about Reinforcement Learning!
I’m not very good at it yet, but I’m still exploring. That’s a very important part of reinforcement learning!
Why do we write/enjoy disturbing content like Kaiji and The Reflecting Skin?
Probably to minimize surprise or something, because we’re bored!