Ching-Yao Chuang
Ching-Yao Chuang
Hi, I simply run the code by `./main.py --task 1` and error occurred. ``` Traceback (most recent call last): File "./main.py", line 7, in from read_data import read_babi, get_max_sizes File...
In `san_att_lstm_twolayer.py`, we can see that the learning rate is 0.05 initially. In function get_lr(), learning rate will dacay like this ``` lua options['lr'] * (options['gamma'] ** power) ``` However...
Hi Denny, Recently I'm working on continuous control reinforcement learning task. I fillowed the steps in [Continuous MountainCar Actor Critic Solution](https://github.com/dennybritz/reinforcement-learning/blob/fd0776899e42ccd931d448aba5c4fc7dd351d323/PolicyGradient/Continuous%20MountainCar%20Actor%20Critic%20Solution.ipynb) to construct PolicyEstimator(). However the log probability of ```self.normal_dist.log_prob()```...
Normally the output of LSTM will be like [N, T, H], N is batch size, T is length and H is hidden state size. But I only use specific hidden...
Hi, Hope you are doing well! I attempt to reproduce the performance of DBI+Mixup on task 1, 2, 4, and 5. However, the mutual information scores I got are 0.016,...