🚀New work on credit assignment in multi-step reasoning RL post-training🚀
Introducing Self-Reset Policy Optimization (SRPO): i) localize the first wrong reasoning step, ii) reset to that step, iii) learn from counterfactual continuations from there – no external supervision.🧵
@DeployableRL workshop is happening this Friday at @RL_Conference. I will be moderating a panel hosting Minmin Chen, Omer Gottsman, @DanielRuss0, Kaushik Subramanian and Cathy Wu. Please vote here https://t.co/g9cWkH04qQ to push your favorite production RL question to the top!
Do you have a question you've always wanted to ask?
Now is the time! Suggest a question or topic for the panel discussion at the DepRL workshop:
https://t.co/SWbCMECg2C
See you August 9th @RL_Conference 🤖
Do you have a question you've always wanted to ask?
Now is the time! Suggest a question or topic for the panel discussion at the DepRL workshop:
https://t.co/SWbCMECg2C
See you August 9th @RL_Conference 🤖
📢 To ease NeurIPS deadline: Submission deadline for the DepRL workshop @RL_Conference extended. Last chance to submit your work: May 17th, 2024 📢
See you in August!
📢 Submission deadline for the DepRL workshop
@RL_Conference approaching: May 8, 2024📢
Let's understand how to build new things with RL🚀
https://t.co/DaXIETDnam
📢 Submission deadline for the DepRL workshop
@RL_Conference approaching: May 8, 2024📢
Let's understand how to build new things with RL🚀
https://t.co/DaXIETDnam
🤖📢
Students that plan to attend
@RL_Conference & Deployable RL workshop
🤖📢
We will provide financial support to several applicants and cover the conference registration fee.
Please submit a request here:
https://t.co/PMeCjzKZz5
📢 We are organizing the Deployable RL Workshop at @RL_Conference 2024! RL is studied in many settings, but the majority of such solutions are 𝑛𝑜𝑡 eventually deployed. Our workshop seeks to understand why.
📅 Deadline: May 8
Speakers & schedule: https://t.co/NM8Th3RdoD
Interested in learning how RL is currently deployed and how it will be applied in the future? What are the challenges we need to resolve? We are organizing the Deployable RL Workshop @DeployableRL during the RL Conference @RL_Conference this August. More info to follow!
🔨🤖
How RL is currently deployed?
How RL will be applied in the future?
What are the challenges we need to resolve?
🤖🔨
Join us in the Deployable RL workshop @RL_Conference in picturesque Amherst to explore these questions
@RL_Conference 📚🤖
~Call for papers~ submission deadline May 8th
📚🤖
We highly encourage sharing your work with the community in the poster session
Additional details: https://t.co/DaXIETDUZU