search

LARG / HFO

Half Field Offense in Robocup 2D Soccer
MIT License
228 stars 93 forks source link

practical high-level features don't match manual #65

Closed kxxwz closed 6 years ago

kxxwz commented 6 years ago

Hi @mhauskn ! When I ran an offense agent in a high-level HFO environment without any npcs, I got 12-dimension state features like this `array([-0.03996074, -0.40227264, -0.3277778 , -0.8333333 , 0. , -1. , 0.00256383, 0.15930545, -0.7506865 , -2. ,

  1. , 0.98625004], dtype=float32). But the manual says I should get a total of10 + 6T + 3O` high-level features, which is 10 high-level features in this case. What are the last two features I got in practice? Thanks a lot!
mhauskn commented 6 years ago

The manual is a bit out of date. A couple additional features were added - I'll refer you to the commit history.

On Thu, Jul 19, 2018 at 4:28 PM Hongjie notifications@github.com wrote:

Hi @mhauskn https://github.com/mhauskn ! When I ran an offense agent in a high-level HFO environment without any npcs, I got 12-dimension state features like this array([-0.03996074, -0.40227264, -0.3277778 , -0.8333333 , 0. , -1. , 0.00256383, 0.15930545, -0.7506865 , -2. , 1. , 0.98625004], dtype=float32). But the manual says I should get a total of 10

  • 6T + 3O high-level features, which is 10 high-level features in this case. What are the last two features I got in practice? Thanks a lot!

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/LARG/HFO/issues/65, or mute the thread https://github.com/notifications/unsubscribe-auth/AABNOWx65Znf6SLg8MMM18KPhgJKxlaoks5uIRYggaJpZM4VXPO0 .

DurgeshSamant commented 6 years ago

Refer PR #66

kxxwz commented 6 years ago

@mhauskn @DurgeshSamant Great! Thank you very much!