Commit Graph
3 Commits
Author SHA1 Message Date
yangdsh a3833d83b1 normalize reward; square reward 2019-10-14 17:52:04 -04:00
yangdsh 090387a176 change the expected value in ddpg test 2019-10-14 17:52:04 -04:00
yangdsh f071a0e62c modify the hyper parameter and reward of ddpg 2019-10-14 17:52:04 -04:00