6 Commits (master)

Author	SHA1	Message	Date
Edward Shen	deb74da552	much refactor	2020-04-05 23:39:19 -04:00
Edward Shen	710a7dbebb	make qlearning train_agent specific	2020-04-05 20:18:48 -04:00
Edward Shen	f3b48fbc85	finish approx q learning	2020-04-05 16:34:33 -04:00
Edward Shen	ce65afa277	use dynamic dispatch for actor selection	2020-04-05 13:31:05 -04:00
Edward Shen	b4660d9f45	qlearning	2020-03-30 17:23:51 -04:00
Edward Shen	4444af9d07	actor implemented	2020-03-30 12:28:53 -04:00