Pieter Abbeel ✓

@pabbeel · Berkeley, CA · joined 21 Aug 2010

Berkeley & Amazon

125 436Followers

465Following

2 690Posts total

753.6KViews on collected posts

Latest posts

Pieter Abbeel ✓@pabbeel10 Jul

Check out ABC Box: i2rt offers a robot setup nicely compatible with ABC data/training infra, even easier to get started! https://t.co/gIn2nnjMTB 29K views · 114 likes · 15 reposts · 8 replies Open on X →

Pieter Abbeel ✓@pabbeel1 Dec 2025

Open-source: complete codebase covering multiple simulation backends, training, retargeting, and real-world inference. Infra built for humanoid, but also readily modified for quadruped (also included). Lots of infra gems/conveniences we rely on consistently. Hopefully equally 77.6K views · 474 likes · 51 reposts · 9 replies Open on X →

Pieter Abbeel ✓@pabbeel1 Dec 2025

Sim-to-real learning for humanoid robots is a full-stack problem. Today, Amazon FAR is releasing a full-stack solution: Holosoma. To accelerate research, we are open-sourcing a complete codebase covering multiple simulation backends, training, retargeting, and real-world https:/ 216.3K views · 600 likes · 132 reposts · 19 replies Open on X →

Pieter Abbeel ✓@pabbeel21 Oct 2025

very excited about the upgrade GaussGym provides for environments for training locomotion capabilities 21.8K views · 134 likes · 12 reposts · 1 replies Open on X →

Pieter Abbeel ✓@pabbeel21 Oct 2025

Simulation drives robotics progress, but how do we close the reality gap? Introducing GaussGym: an open-source framework for learning locomotion from pixels with ultra-fast parallelized photorealistic rendering across >4,000 iPhone, GrandTour, ARKit, and Veo scenes! Thread 🧵 ht 109.5K views · 343 likes · 67 reposts · 11 replies Open on X →

Pieter Abbeel ✓@pabbeel8 Oct 2025

never miss a @xbpeng4 release 23.9K views · 177 likes · 9 reposts · 1 replies Open on X →

Pieter Abbeel ✓@pabbeel8 Oct 2025

Implementing motion imitation methods involves lots of nuisances. Not many codebases get all the details right. So, we're excited to release MimicKit! https://t.co/7enUVUkc3h A framework with high quality implementations of our methods: DeepMimic, AMP, ASE, ADD, and more to come! 171K views · 775 likes · 142 reposts · 9 replies Open on X →

Pieter Abbeel ✓@pabbeel1 Oct 2025

Very excited to start sharing some of the work we have been doing at Amazon FAR. In this work we present OmniRetarget, which can generate high-quality interaction-preserving data from human motions for learning complex humanoid skills. High-quality re-targeting really helps 104.5K views · 352 likes · 43 reposts · 27 replies Open on X →

Against accounts of the same size

1 posts from the last 90 days, next to the 100K–1M follower range. shown widely, but few of those viewers react.

Median views29 020this account4 254median for 100K–1M

Reach, %23.14%this account1.66%median for 100K–1M

Engagement, %0.48%this account1.34%median for 100K–1M

Metric	This account	Median for 100K–1M	Ratio
Median views per post	29 020	4 254	6.82×
Reach (views ÷ followers)	23.14%	1.66%	13.9×
Engagement rate	0.48%	1.34%	0.36×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

104.5K1 Oct

171K8 Oct

23.9K

109.5K21 Oct

21.8K

216.3K1 Dec

77.6K

29K10 Jul

Last 8 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.41%1 Oct

0.55%8 Oct

0.78%

0.40%21 Oct

0.68%

0.36%1 Dec

0.69%

0.48%10 Jul

Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 1.34%.

What the audience does

Likes71.6%2 969 in total

Reposts11.4%471 in total

Replies2.0%85 in total

Quotes2.0%81 in total

Bookmarks13.1%542 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.