-
@btaba
hi bro:
I am on the task of racetrack problem in Sutton's RL book with the method of on-policy monte carlo. However, I find it hard to assess the performance of training process. Is the…
-
Why not hooking up a WS2812 LED Stripe to the first node?
1. Pilot Colors
Every Pilot gets a color and the start gate will shine in the pilots color when passing it.
2. Visual Countdown
add…
ps915 updated
6 years ago
-
hi @btaba :
Have you tried Q-learning on the task like racetrack? I think the problem like monte-carlo off-policy algorithm on this kind of task should not gonna happen with Q-learning.
B…
-
Hi @btaba:
I have tried average return per episode and total return per episode on about 100 episodes and see what happens. They are all like random vibration. Is the episode number too small. See…
-
hi @btaba:
Have you ever try off-policy method on racetrack problem? I tried but found the performance is so bad.
I found something that seems important in Sutton's book :
> The of…
-
**Operating system or device - Godot version:**
Godot 3.0 Alpha, Windows 10, Wacom Cintiq Companion 2
**Issue description:**
When I was attempting to make a 3D racetrack demo using PBR, I par…
-
When editing an existing pitch which is simply tagged leisure=pitch, you type the sport in the sport field. However unlike the main preset list, which adds sport=soccer when searching for football, th…
-
When a Producer is stopped and started again, it does not yield elements until all child iterators (or more precisely the listeners on those iterators (the "drivers")) have ended due to the total deta…
-
when a spin chain file is read in, the first image is kept and the chain is appended. If more than one image were present, all but the first are deleted/replaced.
Logfile:
2017-06-06 22:19:01 […
-
This is a common way of publishing hourly schedules:
http://eurekatransit.org/schedules/ets_weekday_Mar_2013.html
Times at stops are expressed as minutes after the hour.
![red route 1](https:/…