List your company

Continuous Control on OpenAI Gym Mujoco 200K steps v2 (train)

1,000InvertedPendulum-v2 ReturnSSPG
961.52971.51981.5991.49Oct 13, 2022

Evaluation results

MethodLinks
SSPGUTD ratio=10, Random seeds=5, Test rollouts=1002022.101,0003,4874,79310,3095,5135,148
REDQUTD ratio=20, Random seeds=5, Test rollouts=1002022.101,0003,0602,9696,6333,7924,721
IAPORandom seeds=5, Test rollouts=1002022.101,0004265705,303118390
SAC-20UTD ratio=20, Random seeds=5, Test rollouts=1002022.101,0003,3563,0397,1871,801405
MBPOUTD ratio=20, Random seeds=5, Test rollouts=1002022.109633,3034,03410,6704,3093,316