Chengyang Ying

icon indicating a website link https://yingchengyang.github.io/

icon company Tsinghua University icon location Beijing, China icon location PhD Student @ Tsinghua University, Machine Learning, Reinforcement Learning, Embodied AI

Results 5 issues of Chengyang Ying

How to change the reward function in control suite

2 comment

Is it possible to change the reward function of an environment while the sim is running without creating an entirely new physics environment? Any help would be appreciated. Thanks!

Multi-task Environments

Thanks for open-sourcing this! In the paper (arXiv 2102.11271), there are experiments in multi-task setting (Walker-Run Forward&Run Backward&Flip Forward&Flip Backward, and Reach-Duplo Top Left&Top Right&Bottom Left&Bottom Right). How can I...

About the success rate reported in the paper

2 comment

Thanks a lot for providing such wonderful work and clean codes! I'm curious about the results of the success rate reported in the paper. Are these success rates evaluated in...

How to build uphill in DMControl

Thanks a lot for such a wonderful environment. I'm curious about how can we design an uphill with a certain degree (like 30 degrees) in some tasks like Cheetah-run. Thanks...

How to acquire the original document from the uuid

Thanks a lot for such wonderful work. I have tried the code, including encoding and search, as the code has mentioned, I have got a txt file including lines like...