/top/
/new/
/best/
/ask/
/show/
/job/
^
slacker news
login
about
←back to thread
Full Autopilot in GTA Using TensorFlow
(littlemountainman.github.io)
486 points
littlemtman
| 2 comments |
12 May 20 15:17 UTC
|
HN request time: 0.506s
|
source
Show context
wigl
◴[
12 May 20 16:46 UTC
]
No.
23156132
[source]
▶
>>23154886 (OP)
#
What ever happened to the OpenAI/universe GTA sandbox? Is there any reason Rockstar shouldn’t support research using their game?
replies(5):
>>23156270
#
>>23157019
#
>>23157219
#
>>23158845
#
>>23160561
#
littlemtman
◴[
12 May 20 16:55 UTC
]
No.
23156270
[source]
▶
>>23156132
#
If there was a nice solution for it, I would have done it but there isn't. Also the action space for that would be enormous. Maybe I will be making a MuZero Bot drive in GTA, that would be fun !
replies(1):
>>23156984
#
1.
wigl
◴[
12 May 20 17:40 UTC
]
No.
23156984
[source]
▶
>>23156270
#
Did some searching around and found a hidden fork, have you tried this?
https://github.com/Alpha-Drive/universe-windows-envs/tree/ma...
replies(1):
>>23163795
#
ID:
GO
2.
littlemtman
◴[
13 May 20 05:35 UTC
]
No.
23163795
[source]
▶
>>23156984 (TP)
#
Yes I have, but I would prefer a really clean Gym Env for just vehicles in GTA, with an understandable action space.
↑