Yunchu
@yunchuzh
PhD @uwcse || Former MS @CMU_Robotics
ID: 719200768658530304
http://yunchuzhang.github.io 10-04-2016 16:30:00
30 Tweet
143 Followers
160 Following
How can we train RL agents that transfer to any reward? In our NeurIPS Conference paper DiSPO, we propose to learn the distribution of successor features of a stationary dataset, which enables zero-shot transfer to arbitrary rewards without additional training! A thread 🧵(1/9)
🚨Tired of binary pass/fail metrics that miss the bigger picture? 🤖Introducing #RoboEval — an open benchmark that shows *how* robot manipulation policies behave and *why* they fail, not just *if* they succeed. 🧵1/n 🔗 robo-eval.github.io 📄 robo-eval.github.io/media/RoboEval…