The Oopsie Data and workshop team is hosting a little get together tomorrow night after the CoRL workshops! RSVP and come on by!
partiful.com/e/4GI5W0iobUj83…
118
Max Rudolph retweeted
What makes reinforcement learning efficient for training generalist robot policies? A key ingredient is the action representation: what choices do we give the learner to explore? A suitable action representation can make the learning problem substantially easier. 🧵(1/6)
I am so excited about the possibilities from this data...
Max Rudolph retweeted
In our Nature paper, we introduce the first superhuman Stratego AI, which we built using general techniques that we developed for RL & test-time compute under imperfect information. 1/N
Max Rudolph retweeted
On the job market for Research Scientist roles in AI/ML. My PhD focused largely on RL, synthetic data, distribution shift, and OOD detection across robotics, vision, and language. Looking for hands on, energetic and research focused roles! DMs are open if my profile is a match!
Max Rudolph retweeted
During my PhD and time at big tech labs, I approached robot manipulation one robot and one task at a time. We could teach robots new behaviors, but they were slow, limited to one or a few robots, and rarely made it beyond the lab.
At Reward AI, we see cross-embodiment and efficiency as first-class citizens to deploy millions of robots in the real world. And they won't all share a single form factor. With our OM model series, we are bringing human-level efficiency and generalization to any robot.
Max Rudolph retweeted
As of last week we had 54 signed up labs with 10k+ contributed episodes, and as of this week we have 15k+ episodes (140h). Thanks to all of our contributors for continuously logging their data, and excited for what's to come!
Still time to sign up: oopsie-data.com
Replying to @zhiyuan_zhou_
So we're pooling it. We are announcing ✨OopsieData✨, a multi-lab effort to collect real-world manipulation rollouts — suboptimal successes and failures alike — across robots and labs. 17 labs have already contributed, and now it's open to everyone!
We think robot failures are key to robot success at the "Oops, I Erred" workshop at CoRL 2026 in Austin, TX! Consider submitting and joining us!
🤖 Coming to @corl_conf 2026: The first workshop on imperfect robotics data! We’ll explore how to collect, curate & use failures 💢, OOD events❓, and unexpected human behavior 🤔 - data every lab produces but rarely documents, shares, or reuses. Check out workshop.oopsie-data.com
11
864
Very excited to see what robot failures everyone has in store! This is a great opportunity to be a part of a high impact robotics effort for the whole community.
If your robot doesn't get 100% success 100% of the time, then your data can help the community! Sign up at oopsie-data.com and join us in contributing.
57
Max Rudolph retweeted
This is a robot failing to grasp a ball. Almost every robot lab produces clips like this daily… and almost all of them get thrown away. This is the most abundant but underused resource in robot learning. We’re collecting all of it now as ✨OopsieData✨, please join us!
We also release code for benchmarking!
github.com/gabrfarina/exp-a-…
Simple deep RL was thought to fail in imperfect-info games like poker.
A new ICLR 2026 paper shows that with proper tuning, generic methods like PPO match or beat specialized approaches like fictitious play and counterfactual regret minimization.
arxiv.org/abs/2502.08938
1/2
9
710
Max Rudolph retweeted
Two BIG updates for the RLBrew Workshop at #RLC2026! 📣
1️⃣ Dual submissions are welcome
2️⃣ We’ll be awarding a Best Paper RLBrew Award 🏆
You have 2 DAYS LEFT to submit — deadline: May 29!
Details: rlbrew-workshop.github.io/
Max Rudolph retweeted
Reminder! RLBRew deadline in coming up in 7 days! Submit your works soon👩💻
Reminder that we accept under review papers! This is a good place to discuss your ideas and get feedback from the community
Max Rudolph retweeted
We are extending the submission deadline to May 29, 2026 (AoE). Submit your ideas soon!
Scalar, well-defined, easy-to-optimize rewards aren’t always available in real-world interaction data–yet that data is crucial for scaling general-purpose agents. Excited to announce the 3rd edition of RLBRew: Towards Scalable General-Purpose Agents at @RL_Conference 2026!
Max Rudolph retweeted
We welcome diverse perspectives. Your contribution would be invaluable! 🙏
📢 Call for papers: Continual RL Workshop @ RLC 2026, Montreal
🗓️ Submission deadline: May 22, 2026 (AoE)
🔗 Website & CFP: sites.google.com/view/contin…
#ReinforcementLearning #ContinualLearning #MachineLearning #RLC2026 #ContinualRL
Max Rudolph retweeted
Come say hi at my @iclr_conf poster (Friday 10:30am, Pavilion 3 #316) to chat about prediction sets or why @PlantNetProject is my favorite plant identification app!
New paper: Conformal prediction for long-tailed classification🐒
arxiv.org/abs/2507.06867
🧑🌾 (plant enthusiast): Help me identify plants!
🤖 (existing conformal algs): Do you want sets that never include rare plants or sets that contain 100s of labels?
🧑🌾: Uhh… neither? A🧵(1/n)
Presenting Reevaluating Policy Gradient Methods in IIG @iclr_conf ! Come by poster 4418 tomorrow at 10:30 if you want...the (exp-a-) spiel
Work done with @nathanlichtl @___sobhan___ @alexandrebayen , @zicokolter, @yayitsamyzhang @gabrfarina @EugeneVinitsky and @ssokota
We ran thousands of sweeps to compare RL algos for imperfect information games and found preliminary evidence for the Policy Gradient Hypothesis:
With proper tuning, generic PG (PPO, etc.) methods are highly competitive in IIGS.
Check out the full paper: arxiv.org/abs/2502.08938
Max Rudolph retweeted
🔥 Thrilled to announce the Continual Reinforcement Learning (CRL) Workshop @continual_learn, at
@RL_Conference 2026 in Montreal, Canada!
📣 We welcome submissions on broad topics of continual RL. Interested in submitting or reviewing? Check out our website for more details!
Standard RL assumes a stable world. The real world may not.
♾ Introducing the Continual RL Workshop @RL_Conference 2026, Montreal, Canada.
🤖 Agents should never stop learning!
🖼️ Site: sites.google.com/view/contin…
📄 Submit: sites.google.com/view/contin…
























