Kyle Morgenstein

I think the bigger trap is to assume that a modular approach is the answer. For so many locomanip tasks the way we move our body depends so heavily on our environment + goals. I wouldn’t be satisfied to say “let RL handle task agnostic motion and just receive commands from a high level planner”.

For purely “move your body like this to location X” yeah I think current methods will scale. But once you start task conditioning (esp in human environments) I think it’s a lot less clear, both in terms of what behaviors we even want and how to specify them.

GitHub - zita-ch/bipedal-robot-learning-collection: Collection of high-quality robo learning papers for bipedal robots. Collection of high-quality robo learning papers for bipedal robots. - zita-ch/bipedal-robot-learning-collection

Collection of biped locomotion+ RL papers

github.com/zita-ch/bipe...

can we please stop blaming squids for capitalism they are just solitary invertebrates and it's not their fault

I’m using on shape as well since it’s free for me as a student!

Thanks for the insights, I’ll try!

once I have the basic idea and a little confidence I’m pretty good at self directing new projects, but starting is hard

honestly I think what would help me most is a list of increasingly difficult things to make that require more and more tools etc the same way intro coding classes give you assignments that use more and more features of the language.

one of my New Year’s resolutions is to CAD more. I never learned in school but have futzed around with it a bit to make some simple designs to 3D print. would love any tips/recommendations/tutorials etc. that helped you learn!

meant to sleep 4 hours ago 🙃

Amazing post. One suggested addition, please please use data classes whenever possible instead of dictionaries. Raw dictionaries cannot be inspected without running the code and printing the keys. But data classes are basically self documenting! (And they can be typed).

A short list of tips for keeping a clean, organized ML codebase for new researchers: eugenevinitsky.com/posts/quick-...

BE AWARE: SEALION (YOUNGSTER) This little fella likes to jump out of the bushes at you!

The sealion in question

I love this town.

living in a city where the river never freezes >>>

anyways I went on a 13.4 mile walk today. maybe I will graduate soon.

I always feel burn out creep up at the end of the semester and the “take basic care of yourself” special continues to work wonders

I regret to report that sleeping, drinking water, going on long walks, and working out continues to work wonders for mental health

I’m so glad I live during the period of human history in which we invented YouTube. I just watched a documentary about butter.

I suppose this is another way of saying that I’m grateful to have turned in my last graded problem set ever!

didn’t feint after having my blood drawn everyone say yayyy

But now I have to actually think about what I want my robot to do womp womp

Vs.

Now I get to think about what I want my robot to actually do!!

me texting gab:

I know a “prove you’re not a robot” test hate to see me coming

Maia-core and flylist pilled

Or is that Sprigatito

Yoshi at the top of the food chain

there’s only two things in the world I’m flagrantly a snob about: bagels and latex formatting

I suspect you’re right

proof that god loves us dot jpeg

Picture while rowing early in the morning with Austin draped in fog

Rowing when the water is calm: smooth, elegant, like a ballerina

Rowing when the water is choppy: arggh ye matey we be a pirate crew now 🏴‍☠️

March was your Atmospheric Fantasy Soundtrack phase You were really into artists like Hans Zimmer, Austin Wintory, and SEGA SOUND TEAM.

My Spotify wrapped. contains the Dune soundtrack. And the fucking Sonic the Hedgehog official video game sound track. What the fuck.