Jorge Mendez-Mendez
jmendezm.bsky.social
Embodied lifelong learning (compositionality, RL, TAMP, robotics). Assistant Professor at Stony Brook ECE. Postdoc at MIT CSAIL, PhD from GRASP lab at Penn. https://jorge-a-mendez.github.io
👤 Joined on 18 November 2024
2680
Followers
717
Following
37
Total Posts
📜 Kullanıcı Geçmişi
- 18 Kas 2024, 13:12
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@jmendezm.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
I'd say that's because it's not sparse reward in a meaningful way, in the same way Go in self-play is not sparse in a meaningful way. That is, in Go, your reward is 0 for most time steps and only +1/-1 at end. That sound's sparse, but not from an algorithmic perspective.
Show Post
Interesting thread on LLMs vs classical planning
Show Post
🧩 @jmendezm.bsky.social (Stony Brook University) Talk: Unlocking Lifelong Robot Learning With Modularity Jorge shows how modularity in robotics enables scalable lifelong learning for robots. #RobotLearning #Modularity #EmbodiedAI
Show Post🎉 Announcing the winners of the #CoLLAs2025 Early-Career Spotlight Program! These rising stars are pushing the boundaries of lifelong & continual learning, adaptation, and embodied AI. 👇 A thread introducing their work & talks. #AI #MachineLearning #ContinualLearning #LifelongLearning
Show Post