Chenxi Huang

The doc says when logging to a file it is using threading. However, I found that async file access is available on linux. Can you explain?

It seems the Keras implementation does not use policy gradient algorithm (reinforcement learning), instead it uses supervised learning. The Pytorch implementation uses reinforcement learning. Why?

I suggest you make the following changes to chapter4 gamblers_problem to show multiple best actions: x_axis = [] y_axis = [] ...... # line 63 max_values = np.where(np.round(action_returns[1:], 5)==np.amax(np.round(action_returns[1:], 5)))[0]+1...

Structure learning algorithms have very unstable performance

1

Hi, I am testing bnlearn and found that the structure learning algorithms are very unstable, sometimes they generate very accurate results, sometimes very inaccurate results. I am testing the asia...

Not RL

1

This is not reinforcement learning, this is supervised learning. hist = agent.model.fit(X, y, epochs=200, verbose=1, batch_size=64)

I have a simple python web program which uses jinja2 and Quart, when I run python server_async.py, everything is fine. But when I run python -m flamegraph -o perf.log server_async.py,...

I have a simple python web program which uses jinja2 and Quart, when I run python server_async.py, everything is fine. But when I run python -m flamegraph -o perf.log server_async.py,...