Reinforcement Learning on HalfCheetah fixed linear adversary benchmark leaderboard · SOTA2 Research

Reinforcement Learning on HalfCheetah fixed linear adversary

7,495Average PerformanceTC-M2TD3

Evaluation Results

Method	Links
TC-M2TD32024.06		7,495
TC-RARL2024.06		7,443
TC-M2TD32024.06		6,451
TC-M2TD32024.06		6,365
TC-RARL2024.06		5,301
DR2024.06		5,290
TC-RARL2024.06		4,881
M2TD32024.06		3,810
M2TD32024.06		3,560
TD32024.06		1,462
RARL2024.06		218
RARL2024.06		-122