Come by our poster for the paper: Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity, where we develop dynamic programming methods for the infinite horizon static CVaR problem.
Happening this afternoon from 2:30 - 4:15 PM in Hall A, poster #209 #ICML2026
@EstherDerman@pierrelux If you're interested in discussing reasoning under uncertainty, long term credit assignment or applications of risk measures, please reach out and we can get coffee in Seoul!
Reminder that the deadline for the Finding the Frame workshop @RL_Conference is coming up on May 22 AoE ⏰
We're excited to read your submissions reflecting on the philosophy, practice, and formalisms of reinforcement learning!
🔗 More details: https://t.co/mNy0SGK1H2
Finding the Frame will be back at @RL_Conference 2026 with a fantastic speaker lineup! We welcome submissions that reflect on the philosophy, practice, and formalisms of reinforcement learning.
📅Submission deadline: May 22, 2026 (AoE)
More details: https://t.co/bYbIW3QKB7
The great people at @wairobotics are organizing a hackathon for women (students) to learn about robotics. I am organizing a branch at Mila Nov 4-6. If you are interested, please sign up. #Robotics
https://t.co/VkzcseYP5F
That's a wrap! Thank you to all our students/postdocs, employees and to our amazing partners @ahead_io and @nvidia who helped prepare and run the first edition of our Robotics Summer School, organized by Professor @GlenBerseth!
ArXiv https://t.co/pWZDQVFL4X: Transfer learning for RNNs. Taylor expansion around solution where linear correction term (Jacobian) adjusts to the new dynamics given new data. Assumption: parameters for new dynamics are only slightly different from previous ones.