RSSAmplifier

Blog

Home on Arthur Allshire

Recent content in Home on Arthur Allshire

allshire.orgRSS feed ↗11 posts

Latest posts

Bets

L earning Mandarin 
 
 If by 2030, Arthur Allshire is able to have a conversation with 刘靖洲 in Mandarin, 靖洲 will pay Arthur CA$100, inflation adjusted. In the event that he is unable to, Arthur will pay 靖洲 the same amount. 
 
 C limate Change 
 
 w/ Martin Staadecker. Terms TBD 
 
 B ets with Ankur Handa (content to be revealed at resolution): 
 R obotics…

Practical Tips for Getting Reinforcement Learning Algorithms to Work

RL algorithms are a nightmare to get working, below are some of my notes on how to get them to run effectively - 
 
 
 Use delta-based rewards instead of kernels. For example, if you are trying to get a manipulator to a certain point $\vec{x}$, $r(t) = -k (x_{t-1} - x_t)$. In my experience this works better than rewards of the form $r(\vec{x})=f(\vec{x})$. I suspect this is because the…

Subscribe

From time to time, usually when I write new things on this site, I will send out an email. If you want to recieve these, subscribe below: 

 
 
 

	
 
	 
 	
 
 
 
 

 
 
 
 
 




Snippets

My continually updated list of thoughts, comments, and open-questions are a bit to short for a full post and/or which I haven’t had time to properly research/back up which are still worth having online. 
 If you have answers to any of the questions or improvements to any of the ideas, send me your comments via email / Twitter . 
 
 Contents 
 
 
 On that Neuralink…

Linked

Fun links and books, approximately in reverse chronological order by time of reading. Recently I’ve started to track books I’ve read on Goodreads which is probably more up-to-date than this. 
 Dan Wang’s Blog - I particularly resonate with the areas where he advocates that physical-world progress > digital innovation. 
 On Robots 
 Underactuated Robotics 
…

Hobbies


 Astrophotography - here’s a photo I took 
 
 
 
 Running 
 Bouldering 
 Reading 
 Following Formula 1 
 No hiding that I’m a pretty massive nerd so I’m always working on random technical projects on the side… here’s one of the first that exists on the internet. 


How to Learn Things


 
 The forgetting curve for memory. Public Domain. 
 
 
 Contents 
 
 
 Creating Understanding 
 
 Transcription 
 Spaced repetition systems [SRS] 
 Writing 
 Teaching 
 Those exercises at the end of the chapter that you probably want to skip 
 Practical experience 
 
 
 Information Ingestion 
 
 Books 
 Blogs…

Getting started in Robotics


 
 Boston Dynamics' Spot Mini Robot. CC 
 
 People sometimes ask me for robotics resources. There aren’t many high quality internet-first lists available on this topic, so I made one I can link to. I’ll continually update this list so feel free to give suggestions if things are missing or you have better links . 
 There’s some more interesting comments on this…

Teleoperation


 “You can always tell how serious a company is about unmanned by how seriously they talk about teleop” a vendor once told me. Nevertheless, we found an incredible amount of industry and investor resistance to our teleop-dependent approach. Source 
 
 The dream of full autonomy is a compelling one for us roboticists, but I wonder whether it is a practical one if you are looking for…

Robotics should look beyond self-driving

So, I want to talk about safety and autonomy. I am not an expert on this topic (though I do have a background in robotics), but some larger considerations are being missed in the current debate. People go back and forth on how long it will be until Level-4 self driving “arrives”. But nobody ever steps back to the meta-level to consider if this was the right problem in the first place.

GDP Wordle Game

// config.toml (add these settings)
[markup.goldmark.renderer]
unsafe = true 
 // static/css/gdp-wordle.css
.recharts-wrapper {
margin: 0 auto;
}