Jump to: navigation, search

Difference between revisions of "Ad Hoc Teamwork: HFO"

(Limited Half Field Offense)
Line 6: Line 6:
  
 
== Limited Half Field Offense ==
 
== Limited Half Field Offense ==
In the limited half field offense task, 2 offensive agents play against 2 defensive agents, including the goalie.  In these videos, the defense is using behavior designed by Helios.  We sample teammates coming from 2 different teams for the videos.
+
In the limited half field offense task, 2 offensive agents play against 2 defensive agents, including the goalie.  In these videos, the defense is using behaviors designed by Helios.  We sample teammates coming from 2 different teams for the videos.
  
 
'''Cooperating with a teammate designed by Cyrus:'''
 
'''Cooperating with a teammate designed by Cyrus:'''
Line 25: Line 25:
  
  
 +
== Full Half Field Offense ==
 +
In the full half field offense task, 4 offensive agents play against 5 defensive agents, including the goalie.  In these videos, the defense is using behaviors from the agent2d code release.  We sample teammates coming from 2 different teams for the videos.
 +
 +
'''Cooperating with teammates designed by Helios'''
 +
 +
Combined Policy:
 
{{#ev:youtube|hYKyjJXAI88}}
 
{{#ev:youtube|hYKyjJXAI88}}
  
 +
PLASTIC-Policy:
 
{{#ev:youtube|Bhj-h3bgeDk}}
 
{{#ev:youtube|Bhj-h3bgeDk}}
  
 +
'''Cooperating with teammates designed by Gliders'''
 +
 +
Combined Policy:
 
{{#ev:youtube|U3ENo7Rxw0I}}
 
{{#ev:youtube|U3ENo7Rxw0I}}
  
 +
PLASTIC-Policy:
 
{{#ev:youtube|ITHkok9pfGw}}
 
{{#ev:youtube|ITHkok9pfGw}}

Revision as of 22:23, 13 October 2014

Ad hoc teamwork in the Half Field Offense (HFO) task in the 2D simulated RoboCup domain.

Original specification of the HFO task.

In this research, we investigate the performance of PLASTIC-Policy in the HFO domain. PLASTIC-Policy learns policies for cooperating with past teammates and selects from among these policies on the fly. In these videos, PLASTIC-Policy has learned about 7 previous types teammates. As a baseline, we compare the performance of the Combined Policy, where the ad hoc agent combines its observations about all 7 types of teammates to learn a new policy.

Limited Half Field Offense

In the limited half field offense task, 2 offensive agents play against 2 defensive agents, including the goalie. In these videos, the defense is using behaviors designed by Helios. We sample teammates coming from 2 different teams for the videos.

Cooperating with a teammate designed by Cyrus:

Combined Policy:

PLASTIC-Policy

Cooperating with a teammate from the agent2d code release:

Combined Policy:

PLASTIC-Policy:


Full Half Field Offense

In the full half field offense task, 4 offensive agents play against 5 defensive agents, including the goalie. In these videos, the defense is using behaviors from the agent2d code release. We sample teammates coming from 2 different teams for the videos.

Cooperating with teammates designed by Helios

Combined Policy:

PLASTIC-Policy:

Cooperating with teammates designed by Gliders

Combined Policy:

PLASTIC-Policy: