kono
55d8bbf5dc
add Random-, Greedy and EGreedy-Policy and first implementation of monte carlo method
...
- fixed bug regarding wrong generation of hashCode. hashCodes needs to be equal across equal objects. Compute hashCode on final states once and return this value instead of computing it every time .hashCode() gets called.
-
2019-12-09 23:21:48 +01:00
kono
0100f2e82a
remove the Action interface in favour of Enums
2019-12-09 17:30:14 +01:00
kono
8a533dda94
change ActionSpace interface temporarily to quickly fit antWorld test and improve gui of walking ant
2019-12-09 13:41:00 +01:00
kono
2fb218a129
add separate class for intern Ant representation and adopt gui cell size to panel size
2019-12-09 12:08:53 +01:00
kono
c11cc2c3f2
add two simple scroll panes to represent environment and ant brain
2019-12-09 01:09:34 +01:00
kono
db9b62236c
add logic to handle ant action and compute rewards
...
- ant world will handle and compute action received by the agent
- first try to convert observations to markov states
- improved .equals() methods
2019-12-08 16:03:00 +01:00
kono
ec67ce60c9
add default structure for AntAgent
2019-12-08 13:15:20 +01:00
kono
581cf6b28b
Merge remote-tracking branch 'origin/master'
2019-12-07 22:08:20 +01:00
kono
87f435c65a
add basic core structure and first parts of antGame implementation
2019-12-07 22:05:11 +01:00
kono
431ae4d3df
add basic core structure and first parts of antGame implementation
2019-12-07 17:31:30 +01:00
kono
66ee33b77f
init the gradle project
2019-12-06 13:11:29 +01:00
kono