Qingfeng Lan

icon indicating a website link https://lancelqf.github.io/about/ icon indicating an email [email protected]

icon company University of Alberta icon location Edmonton, Canada icon location Working on Reinforcement Learning @ RLAI Lab, University of Alberta.

Results 5 comments of Qingfeng Lan

RuntimeError in torchnlp.nn._weight_drop wrapped by torch.nn.DataParallel

Similar problem here. When I try to use WeightDropGRU and move it to GPU, I get an error: AttributeError: 'WeightDropGRU' object has no attribute '_flat_weights' Any idea how to solve...

Replication of Mogrifier LSTM paper

Thank you for your detailed reply! I've emailed the author.

Replication of Mogrifier LSTM paper

Thanks!

[Feature Request] Running XLA functions on TPU

I encountered the same problem.

Significant changes in scores with the v0.0.11 physics

With Brax 0.9.3, PPO can only achieve 3000 in HalfCheetah with the implementation and hyper-parameters provided in the notebook, much lower than previous return (~8000).