8 Commits

Author	SHA1	Message	Date
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
Jan Löwenstrom	7db5a2af3b	add fix RNG, add extended interface EpsilonPolicy and move rewardHistory to model instead of view ... - only setting the seed of RNG once at the beginning and not reseeding it afterwards. Deep copying the initial AntWorld to use as blueprint for resetting the world instead of reseeding and creating pesudo random again. Reseeding the RNG has influence action selecting to always choose the same trajectory. - instance of is used to determine if policy has epsilon or not and the view will adopt to this, only showing epsilon slider if policy has epsilon	2019-12-20 16:51:09 +01:00
Jan Löwenstrom	8a533dda94	change ActionSpace interface temporarily to quickly fit antWorld test and improve gui of walking ant	2019-12-09 13:41:00 +01:00
Jan Löwenstrom	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
Jan Löwenstrom	ec67ce60c9	add default structure for AntAgent	2019-12-08 13:15:20 +01:00
Jan Löwenstrom	87f435c65a	add basic core structure and first parts of antGame implementation	2019-12-07 22:05:11 +01:00