Sahil Sharma
Sahil Sharma
When I try to run the saved model as : ``` bash python demo_a3c_ale.py ../roms/breakout.bin trained_model/breakout_ff/80000000_finish.h5 ``` I get an error : ``` bash ImportError: No module named 'ale_python_interface' ```...
Hi, I am running the A3C-lSTM model on the game space invaders. But as can be seen in the [scores dump](http://pastebin.com/k30SeXt3) the model does not seem to learn anything. In...
Hi, After training for about 75000 steps, only 8 episodes have passed and the agent has not learnt anything useful. My question is: does the current `ddpg.py` file have the...
Hi, I believe that in DDPG the Value function output is a single scalar and not same as action size. Hence [this line](https://github.com/yanpanlau/DDPG-Keras-Torcs/blob/master/CriticNetwork.py#L54) in `CriticModel.py` should be ``` V =...
If I understand the code correctly, it uses virtual batch normalization only for the inputs and **not** for the intermediate layers. Was this done in the Atari context for getting...
Hi, Could you please release an example config file for Atari games as well? Thanks!
The `init_params()` [function](https://github.com/openai/improved-gan/blob/master/mnist_svhn_cifar10/train_cifar_feature_matching.py#L102) seems to be buggy because it accepts an argument `x_lab` but does not use it at all. Also the comment reads data based initialization. How is this...
Hi, Im running the code as-is for the InvertedPendulum-v1 environment. The output log looks like: ``` [2016-09-29 02:55:12,968] Making new env: InvertedDoublePendulum-v1 [2016-09-29 02:55:13,029] OpenGL_accelerate module loaded [2016-09-29 02:55:13,076] Using...