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 3 issues of Qingfeng Lan

Replication of Mogrifier LSTM paper

5 comment

Does your code replicate the results in Mogrifier LSTM paper?

The best hyper-parameters for DQN / DDQN / Averaged DQN / Maxmin DQN

| Catcher | DQN | DDQN | Averaged DQN | Maxmin DQN | | ---- | ---- | ---- | ---- | ---- | | lr | 0.0001 | 0.0001...

How to reinitialize the hidden states of RNNs?

I want use `initial_state` in this way but get an error: AttributeError: 'Transformed' object has no attribute 'init_hidden_state' What is the best way to to this? ``` import haiku as...