Finding The Frame Workshop
@RLFrameWorkshop
An @RL_conference workshop for examining conceptual frameworks in reinforcement learning.
🚨 We extended Finding the Frame's submission deadline to June 15 AoE! 🚨 ✨We're looking for bold ideas that rethink the foundations of RL: goals, values, rewards, formalisms, and beyond🚀 More details: sites.google.com/view/findingth… See you @RL_Conference !
*Taps the sign* @RLFrameWorkshop exists for exactly this reason. At the very least RL (not surprisingly, in my very biased opinion) is working to save ML.
Every CS/AI PhD should be required to read Kuhn's Structure. We are a field in a paradigm crisis, much like Physics at the turn of the 20th century. One of the best times to be in a field, one of the worst times to be the field.
Finding the Frame workshop is coming up on Aug. 5 at #RLC2025!🚀 We’re excited to discuss the conceptual foundations of RL with our panelists: Erin Talvitie, George Konidaris, Mark Ho and Clare Lyle. Send in your questions! 📬
🤔 Unsure whether your work fits the spirit of the workshop? ✨ Check out @benplaut’s paper, which tackles online RL without the assumption that all mistakes are reversible. ———— ⏳ Submit by May 30 (AOE)! sites.google.com/view/findingth…
(1/5) New paper! Despite concerns about AI catastrophe, there isn’t much work on learning while provably avoiding catastrophe. In fact, nearly all of learning theory assumes all errors are reversible. Stuart Russell, Hanlin Zhu and I fill this gap: arxiv.org/pdf/2402.08062
🆕at Finding the Frame this year: outstanding paper awards!🏆 We will be highlighting exceptional papers across a few categories, including Most Thought-Provoking🤔 You still have until May 30 to submit- see our website for all the details! sites.google.com/view/findingth…
🤔 Unsure whether your work fits the spirit of the workshop? ✨ Check out @MicahCarroll ’s paper from last year’s workshop on rethinking fundamental assumptions on reward functions! ———— ⏳ Submit by May 30 (AOE)! 🌐 sites.google.com/view/findingth…
Excited to share a unifying formalism for the main problem I’ve tackled since starting my PhD! 🎉 Current AI Alignment techniques ignore the fact that human preferences/values can change. What would it take to account for this? 🤔 A thread 🧵⬇️
True dat
now that RL is hot again, you should all register for RLC and come visit Edmonton in August rl-conference.cc/index.html
🤔 Not sure if your work fits the spirit of the workshop? ✨ Check out a great example: @guyd33’s paper from last year on goal representations! ———— Submit by May 30 (AOE)! ⏳
New paper! @todd_gureckis and I spent some time thinking about what we might want out of goal representations for artificial agents, and the result is here (Oral paper at the RLC Finding the Frame workshop): openreview.net/attachment?id=…
🚨 Reminder! Submissions for @RL_Conference's Finding the Frame are due May 30 (AoE)! We're looking for bold ideas that rethink the foundations of RL: goals, values, rewards, formalisms, and beyond. 🧠Philosophy, theory, critique welcome! 🔗More details: sites.google.com/view/findingth…
✨Recordings of Finding the Frame Workshop at @RL_Conference 2024 are now up on our website!✨ sites.google.com/view/findingth…
In the workshop, we asked panelists: "Can you share a paper or book that changed the way you framed AI problems or has otherwise heavily influenced you as a scientist?" 💡Check out panelist recommendations here!💡 sites.google.com/view/findingth…
Massive turnout for our speakers at the @RLFrameWorkshop! Many people excited about the conceptual foundations of RL. Be sure to check out our panel discussion at 10:40 AM at Room 168. #RLC2024
On the eve of @RL_Conference, some thoughts: 1. If we didn't have this conference, I can't imagine a workshop like @RLFrameWorkshop existing. It's important but just wouldn't fly elsewhere 2. The level of community excitement and involvement has been WILD 1/3
We love this community ❤️ So great to see so many people excited about Finding the Frame!
Massive turnout for our speakers at the @RLFrameWorkshop! Many people excited about the conceptual foundations of RL. Be sure to check out our panel discussion at 10:40 AM at Room 168. #RLC2024