qlearning4k issues

two example not work

2

Hi , I have two problem in ```test_catch.py``` and ```test_snake.py``` - python version : Anaconda3/python3.5 - platform : macOS - backend : Tensorflow In ```test_catch.py``` ```shell== Traceback (most recent call...

RozenAstrayChen

test_snake.py 'Negative Dimension Size caused by...

1

Using TensorFlow backend. Traceback (most recent call last): File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 654, in _call_cpp_shape_fn_impl input_tensors_as_shapes, status) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\contextlib.py", line 66, in __exit__ next(self.gen) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 466, in raise_exception_on_not_ok_status pywrap_tensorflow.TF_GetCode(status))...

gaara100

grid_size incorrect error

we should have `self.grid_size-2` instead of `self.grid_size-1` https://github.com/farizrahman4u/qlearning4k/blob/4c029dd60f0809c689808826ddc40d5e57f5ea7d/qlearning4k/games/catch.py#L36

naouss80

The layer "sequential_1 has multiple inbound nodes, with different input shapes. Hence the notion of "input shape" is ill-defined for the layer. Use `get_input_shape_at(node_index)` instead.

5

Hi I seem to be running `$ python test_catch.py` and here is what I seem to get Epoch 1000/1000 | Loss 0.0104 | Epsilon 0.10 | Win count 793 Traceback...

naouss80

Various algorithms?

4

Will this repo be the place where multiple reinforcement learning algorithms (q-learning, A3C, ...) be implemented for Keras?

ericvrp

NaN Loss on train

4

I have been getting NaN losses when I try to train my agent on a game. I tracked it back to the get_batch function in memory - Y (the output...

bglick13

GPU performance question

2

I noticed that training on CPU-only is much faster than on GPU. With GPU, usage is about 18% according to nvidia-smi. Is this because it trains for each epoch, and...

cjmielke