deep_q_rl
deep_q_rl copied to clipboard
Theano-based implementation of Deep Q-learning
What is the version of numpy did you install? I updated numpy to the newest version: 1.8.2 How to uninstall/ install the right version of numpy?
$ python plot_results.py SEAQUEST_04-24-05-36_0p00025_0p99/learning.csv Traceback (most recent call last): File "plot_results.py", line 22, in plt.plot(results[:, 0], np.convolve(results[:, 3], kernel, mode='same'), '-') IndexError: index 3 is out of bounds for axis...
Loading pkl file on Windows 10 it throws EOF error with 'r' flag. But it works with 'rb' and 'wb' flags just as they wrote here: http://deeplearning.net/software/theano/tutorial/loading_and_saving.html So, please consider...
For people who do not have GPU / CUDA machines
the Lasagne.layers.Conv2DCCLayer used the default nonlinearity(activation), which use non existed theano.tensor.nnet.relu ## The following code is in Line 142, Lasagne.nonlinearities.py # rectify def rectify(x): """Rectify activation function :math:`\\varphi(x) = \\max(0,...
This makes it easier to keep track of experiment configuration and parameters automatically. Note that "git diff HEAD" will include both staged and unstaged changes. Example: ``` ~/dqn/test-runs/version_info_10-02-07-56-18_0p00025_0p99$ cat cmdline...
Simple issue: need ale_nips_run_watch.py. Running the nips training settings but then the nature test settings results in not even working.