Danijar Hafner
Danijar Hafner
I came across `skhd -k "return"` by googling but `skhd -k "ü"`doesn't work. Is there another flag for that?
When trying to solve [this issue](https://github.com/koekeishiya/skhd/issues/285), I tried to list all flags available in skhd but none of these worked: - `man skhd` - `skhd --help` - `skhd -h` Would...
Right now, Ctrl+c does not abort a long session run.
Hi, I'm trying to adopt YAPF for a larger code base and am running into a few edge cases. Is there a configuration option to achieve the following desired output?...
Hi, I'm trying to adopt YAPF for a larger code base and am running into a few edge cases. Is there a configuration option to achieve the following desired output?...
YAPF sometime breaks lines in spots that look a bit odd because they result in a very short and a very long line, whereas breaking the long expression at a...
Right now, the preference order is glfw > egl > osmesa. In the common scenario of training an RL agent on a GPU machine, this means windows will pop up,...
Currently, I have this in my i3 config to run dmenu in my system-wide color scheme: ``` shell bindsym $mod+d exec --no-startup-id dmenu_run \ -fn 'DejaVu Sans Mono:pixelsize=19' \ -nb...
I think you should use `tf.stop_gradient()` in https://github.com/coreylynch/async-rl/blob/master/a3c.py#L164. Otherwise, after some training the policy tends to use one action exclusively. Took me a while to figure this out in my...
You write that one should try experiments with multiple seeds. Did you found that results differ substantially given only different seeds? I'm asking because in the paper, Mnih. et al....