List your company
ResearchFormerly WizWand

Continuous Control on Ant v1 (train)

4,372.44Max Average ReturnTD3
-253.7816947.25672,148.2953,349.3333Feb 26, 2018
Updated 8mo ago

Evaluation results

MethodLinks
TD32018.024,372.44
ACKTR2018.021,821.94
PPO2018.021,083.2
DDPG2018.021,005.3
Our DDPG2018.02888.77
SAC2018.02655.35
TRPO2018.02-75.85