PPO: rejected from NIPS 2017
8:11 AM · Jun 17, 2026 · 32.4K Views
PPO creator John Schulman says the foundational reinforcement learning paper was originally rejected from NIPS 2017
Story Overview
John Schulman just noted that the Proximal Policy Optimization paper, now a cornerstone of reinforcement learning from human feedback, failed to clear the bar for NIPS 2017 even though it later anchored the training recipe behind ChatGPT-style models.
23896717530.6K
Open Question
Why top venues sometimes overlook future classics
Absent the original reviewer comments, which Schulman says are buried in an old inbox, the precise objections remain unknown, so the rejection stands as a reminder that early signals can diverge from lasting influence.
Developer Impact
How PPO quietly shaped modern AI training
The method simplified earlier trust-region approaches while delivering strong results on robotics and game benchmarks, eventually becoming the default policy optimizer inside RLHF stacks that align today's large models.
Sentiment
Many users praised John Schulman as a legend for PPO despite its NIPS 2017 rejection while others called the decision obviously incorrect and peer review flawed.
Pos
60.0%
Neg
40.0%
5 comments with sentiment.
Cluster Engagement
Digg Deeper
No Digg Deeper questions have been answered for this story yet.
Posts from X
Most Activity
Most Activity
VIEWS1.1KLIKES13REPLIES1
Gautam Kamath@thegautamkamath
@johnschulman2 I know people would be interested to see the reviews if you still have them!
2hViews 1.1KLikes 13
BOOKMARKS3
Dhruv Srikanth@DhruvSrikanth
@johnschulman2 I think https://arxiv.org/abs/1503.02531 was rejected as well so its in good company
2hViews 889Likes 6Bookmarks 3
John Schulman@johnschulman2
@thegautamkamath I looked, but unfortunately it's in my openai gmail. maybe @prafdhar has access?
2hViews 1KLikes 10Bookmarks 1
Xiao Ma@infoxiao
@johnschulman2 legend
John Schulman@johnschulman2
PPO: rejected from NIPS 2017
1hViews 1.1KLikes 5Bookmarks 0
Duc Manh Bui@Buimanh22
@johnschulman2 Wow quite surprise for that @@ I think the field changed a lot recently but at that time why PPO could be rejected…
2hViews 639Likes 2
Joseph Suarez 🐡@jsuarez
@johnschulman2 That's where my first conference paper got accepted! I just slammed together two SOTA language modeling methods and got +2%. Peer review in AI was a farce long before LLMs
1hViews 143Likes 3
Pierre Richemond 🇪🇺@TheOneKloud
@johnschulman2 @canondetortugas Happens to the best !
1hViews 416Likes 1
Nasib A. Naimi@NasibNaimi
@johnschulman2 oh boi, doesnt that tell you all you need to know. What reasons did the reviewers state?
1hViews 387Likes 1
Mahaoo@mahaoo_ASI
@johnschulman2 @JoshPurtell offical and obviously incorrect rejection is something that stays with you, many highly successful people remember these years after the fact, despite being of no additional consequences to their own lives
1hViews 284Likes 1
yobibyte@y0b1byte
@johnschulman2
1hViews 93Likes 1
Rafael Pardinas@muchomuchacho
@johnschulman2 PipelineRL: rejected from NeurIPS 2025
1hViews 259
National Champions 〽️🇺🇸🏀@JKSully313
@johnschulman2 I’d kill to see the Openreview (or equivalent) for PPO that got rejected.
1hViews 179
Think_Different_@ThinkDi92468945
@DhruvSrikanth @johnschulman2 That’s nuts (if true)
2hViews 54Likes 1
Bojan Jakimovski@Shekswess
@johnschulman2 Thanks for PPO legend !
1hViews 52
hallerite@hallerite
@johnschulman2 with what reasoning?
58mViews 38