8 Commits
Author SHA1 Message Date
Shangtong Zhang 1be3b44999 Continuous A3C 2017-07-31 22:53:09 -06:00
Shangtong Zhang 353541cd32 Double DQN and Dueling DQN 2017-06-03 15:03:17 -06:00
Shangtong Zhang 45a3f00d32 Optimize replay buffer 2017-05-24 19:45:42 -06:00
Shangtong Zhang de6d52d86f Refactor interfaces 2017-05-05 22:24:51 -06:00
Shangtong Zhang 966e3ebd60 Replace tensorflow with pytorch 2017-05-04 14:05:40 -06:00
Shangtong Zhang 3f13ebc711 Crossprop 2017-05-03 19:48:03 -06:00
Shangtong Zhang 72ef60c076 modularized DQN 2017-04-20 14:03:44 -06:00
Shangtong Zhang 9101ed2eb0 Initial commit 2017-04-20 13:59:53 -06:00