A while ago, I did a post on beating OpenAI games using neuroevolution (NE). Go read that if you’re interested, but here’s the gist: a typical strategy for training an agent to beat those games is to have a neural network (NN) play the games a bunch, and then improve the weights of the NN using a reinforcement learning algorithm that uses gradient descent (GD), and it of course works pretty well.
However, an alternative to those methods is to use a gradient free method (which I’ll call “GD-free”), like I did in that post: you try a bunch of random changes to the NN’s weights, and only keep the resulting NNs that play the game well. That’s the “evolutionary” aspect of it, and using methods like that to create NNs is often called “neuroevolution” (NE).
After I trained an agent to play “puckworld” using Q-learning, I thought “hey, maybe I should make a real robot that learns this. It can’t be that hard, right?”
Hooooooooo boy. I did not appreciate how much harder problems in the physical world can be. Examples of amateurs doing Reinforcement Learning (RL) projects are all over the place on the internet, and robotics are certainly touted as one of the main applications for RL, but in my experience, I’ve only found a few examples of someone actually using RL to train a robot. Here’s a (very abridged!) overview of my adventure getting a robot to learn to play a game called puckworld.
I first heard this puzzle when taking an algorithms class in undergrad. The prof presented it as a teaser for the type of thing you could solve using algorithmic thinking, though he never told us the answer, or what the way of thinking is. Then, it more recently came up with my friends while we were hiking, and we were talking about it. I’ll talk about what I have so far, but first let’s say what the puzzle actually is.
There’s a building with 100 floors. You have two identical crystal eggs. They will break if dropped from (or above) some height (the same height for both), and you’d like to find that height using the fewest number of drops possible. If you drop an egg from some height and it doesn’t break, you can use that egg again. Once an egg is broken (i.e., you dropped it from that breaking height or above), you can’t use that egg again. So the question is, what’s the best dropping strategy?
Genetic Algorithms are cool!
I was recently skimming through Russel and Norvig’s AI: A Modern Approach and came to the section on Genetic Algorithms (GA). Briefly, they’re a type of algorithm inspired by genetics and evolution, in which you have a problem you’d like to solve and some initial attempts at solutions to the problem, and you combine those solutions (and randomly alter them slightly) to hopefully produce better solutions. It’s cool for several reasons, but one really cool one is that they’re often used to “evolve” to an optimal solution in things like design of objects (see the antenna in the Wikipedia article). So, that’s kind of doing evolution on objects rather than living things. Just take a look at the applications they’re used for.
Hey there! It’s been a while. I’ve been working on lots of stuff, but here’s a small thing I did recently.
My friends and I have a Slack we’ve now been using casually for a few years. You can download the entire logs of your Slack workspace, even if you use the free one (which will cut off the messages it shows you after 10,000 messages, I believe). So I wanted to do a few little projects with it.
I started this AI course with my friends a while ago, but we never ended up finishing it. I’m interested in AI these days, so I thought I’d try it on my own. Week 1 is some fluff that’s not worth going over. I’m doing weeks 2 and 3 together because there is one project for both combined. The first couple sections are just notes I took on the videos and concepts. The stuff for the project is at the bottom.