Matthew Jackson

@JacksonMattT

Robots @OpenAI

985Followers

604Following

121Posts total

121.7KViews on collected posts

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

110.1K18 Apr

1.3K

1.2K

971

5.3K

1.4K

920

473

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

0.21%18 Apr

0.91%

0.85%

1.24%

0.53%

0.64%

2.50%

0.42%

Reactions — likes, reposts, replies and quotes — divided by views.

What the audience does

Likes57.8%260 in total

Reposts10.7%48 in total

Replies2.2%10 in total

Quotes2.2%10 in total

Bookmarks27.1%122 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.

Latest posts

@JacksonMattT Great (and much needed) work! Excited to use this beautiful code! 473 views · 2 likes · 0 reposts · 0 replies 18 Apr 2025 Clean code, fast training, and a unified space - a clean slate for Offline RL. We’re excited to see what you build 🚀 Work co-led with @uljadb99 and @JarekLiesen, in @FLAIR_Ox! 📝 Paper: https://t.co/YycSaRrXi8 💻 Code: https://t.co/vjJdEBY1Qm 920 views · 22 likes · 1 reposts · 0 replies 18 Apr 2025 🔬 Evaluation has been a limiting factor of offline RL, so we also propose a new evaluation protocol, see @JarekLiesen's thread: https://t.co/K0tXyJGiAM 1.4K views · 8 likes · 0 reposts · 1 replies 18 Apr 2025 ⁉️ While trying to find the best hyperparameter setting of ORL algorithms using a bandit, we noticed something unexpected: 🤯 After evaluating the episodic returns of more and more policies online, the bandit's performance *decreased*! https://t.co/LDvyBPyA2d https://t.co/1IKSA4DS 5.3K views · 19 likes · 5 reposts · 1 replies 18 Apr 2025 ⚡️ Naturally, we're all-in on JAX, so training takes minutes, not hours... https://t.co/NJlYwDXn4m 971 views · 11 likes · 0 reposts · 1 replies 18 Apr 2025 💡 Within this space, we discovered two new algorithms - TD3-AWR and MoBRAC - achieving SOTA model-free and model-based performance. https://t.co/2zltJ6lC6g 1.2K views · 9 likes · 0 reposts · 1 replies 18 Apr 2025 🌐 Our unified algorithm brings together a whole ecosystem of model-free and model-based methods - TD3-BC, IQL, EDAC, ReBRAC, MOPO, and more - plus any combination of their components. 1.3K views · 11 likes · 0 reposts · 1 replies 18 Apr 2025 🌹 Today we're releasing Unifloral, our new library for Offline Reinforcement Learning! We make research easy: ⚛️ Single-file 🤏 Minimal ⚡️ End-to-end Jax Best of all, we unify prior methods into one algorithm - a single hyperparameter space for research! ⤵️ https://t.co/tp2gbVVt 110.1K views · 178 likes · 42 reposts · 5 replies 18 Apr 2025

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Latest posts

Similar accounts