Perry Dong ✓

@perryadong

CS PhD @StanfordAILab @GoogleDeepMind | Reinforcement Learning

1 126Followers

110Following

59Posts total

10.8KViews on collected posts

Postingan terbaru

Perry Dong ✓@perryadong9 Aug

@perryadong Because the assumptions behind Q-function do not hold for most real-word conditions, unlike language or image. 533 views · 1 likes · 0 reposts · 0 replies Open on X →

Perry Dong ✓@perryadong30 Jul

To fix this, our key idea: loosen the Q-function's constraint to base-policy actions We propose Initialization via Policy Ensemble (IPE) — initialize Q-function on rollouts from diverse policies, giving it real coverage so fine-tuning learns the RL optimal Q-function (5/6) http 1.9K views · 9 likes · 1 reposts · 1 replies Open on X →

Perry Dong ✓@perryadong30 Jul

Project with Ron Polonsky, @DorsaSadigh, @chelseabfinn Paper: https://t.co/QDlClPfgfv Arxiv: https://t.co/TBmtCqP1bp (6/6) 1.7K views · 25 likes · 1 reposts · 0 replies Open on X →

Perry Dong ✓@perryadong30 Jul

We break down the core reason: the pretrained critic targets the wrong value function Even in the limit of an optimal pretraining distribution, its action preferences diverge from the optimal RL critic's (3/6) https://t.co/PCkOZVLD26 2.1K views · 7 likes · 1 reposts · 1 replies Open on X →

Perry Dong ✓@perryadong30 Jul

Furthermore, fixing pretraining post hoc through offline value maximization is insufficient (4/6) https://t.co/1f5K8HqXop 1.6K views · 5 likes · 1 reposts · 2 replies Open on X →

Perry Dong ✓@perryadong30 Jul

We analyze the performance of pretraining against training from scratch, and show that naive Q-function pretraining does not accelerate fine-tuning (2/6) https://t.co/iC77krarpl 3.1K views · 10 likes · 1 reposts · 1 replies Open on X →

Dibandingkan akun berukuran sama

6 postingan dari 90 hari terakhir, dibandingkan dengan rentang under 10K pengikut. di bawah akun sekelasnya baik pada jangkauan maupun interaksi.

Median tayangan1 780akun ini4 175median untuk under 10K

Jangkauan, %158.04%akun ini250.82%median untuk under 10K

Interaksi, %0.47%akun ini1.41%median untuk under 10K

Metrik	Akun ini	Median untuk under 10K	Rasio
Median tayangan per postingan	1 780	4 175	0.43×
Jangkauan (tayangan ÷ pengikut)	158.04%	2.5× audience	0.63×
Tingkat interaksi	0.47%	1.41%	0.33×

Akun lain pada rentang ini → Bandingkan dengan akun lain → Bagaimana tolok ukur ini disusun →

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

3.1K30 Jul

1.6K

2.1K

1.7K

1.9K

5339 Aug

Last 6 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.39%30 Jul

0.49%

0.44%

1.57%

0.58%

0.19%9 Aug

Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.41%.

What the audience does

Likes71.2%57 in total

Reposts6.2%5 in total

Replies6.2%5 in total

Bookmarks16.2%13 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.

Postingan terbaru

Dibandingkan akun berukuran sama

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Akun serupa