 Jan Löwenstrom
|
ad07c1da8f
|
remove DinoSampling stuff
|
2020-04-05 13:10:13 +02:00 |
|
Jan Löwenstrom
|
5b82e7965d
|
rename MC class and improve specific analysis of antGame examples
|
2020-04-05 12:29:44 +02:00 |
|
Jan Löwenstrom
|
4402d70467
|
Merge remote-tracking branch 'origin/antWorldRewardAnalysis' into antWorldRewardAnalysis
# Conflicts:
# OptimalityDifferentDiscountFactors.R
# src/main/java/core/algo/td/QLearningOffPolicyTDControl.java
# src/main/java/example/ContinuousAnt.java
|
2020-04-05 12:05:15 +02:00 |
|
Jan Löwenstrom
|
b9be640284
|
add multiple folders to organize results
|
2020-04-05 12:00:16 +02:00 |
|
Jan Löwenstrom
|
a08b8160a3
|
add new results of needed timestamps in total
|
2020-04-04 17:14:12 +02:00 |
|
Jan Löwenstrom
|
595451e88b
|
add new results of needed timestamps in total
|
2020-04-04 17:07:43 +02:00 |
|
Jan Löwenstrom
|
740289ee2b
|
add constant for default reward
|
2020-04-02 14:01:37 +02:00 |
|
Jan Löwenstrom
|
f4b50627d1
|
add antGame analysis data and R Scripts and images
|
2020-03-29 17:22:47 +02:00 |
|
Jan Löwenstrom
|
328fc85214
|
modify q Learning to sample results and update R script
|
2020-03-28 12:35:33 +01:00 |
|
Jan Löwenstrom
|
eca0d8db4d
|
create Dino Sampling state
|
2020-03-26 19:22:50 +01:00 |
|
Jan Löwenstrom
|
ee1d62842d
|
split Antworld into episodic and continuous task
- add new simple state for jumping dino, to see if convergence is guarenteed with with state representation
- changed reward structure for ant game
|
2020-03-15 16:58:53 +01:00 |