List your company
ResearchFormerly WizWand

Continuous Control on Reacher v1 (train)

-3.6Max Avg ReturnTD3
-115.7432-86.6291-57.515-28.4009Feb 26, 2018
Updated 8mo ago

Evaluation results

MethodLinks
TD32018.02-3.6
Our DDPG2018.02-4.01
ACKTR2018.02-4.26
SAC2018.02-4.44
PPO2018.02-6.18
DDPG2018.02-6.51
TRPO2018.02-111.43