Offline Reinforcement Learning on halfcheetah Mixed Dataset benchmark leaderboard · SOTA2 Research

Offline Reinforcement Learning on halfcheetah Mixed Dataset

74.5Normalized RewardMOBILE

Evaluation Results

Method	Links
MOBILE2024.06		74.5	64.7
MOMBO2024.06		73.5	69.3
MOPO2024.06		73.4	68.4
MOBILE2024.06		72.9	47.3
MOBILE2024.06		72	67.3
MOMBO2024.06		68	61.2
MOPO2024.06		66.2	59.5
MOBILE2024.06		65.4	59.9
MOBILE2024.06		62.4	56.4
MOMBO2024.06		62.2	58.1
MOPO2024.06		62.1	54.3
MOMBO2024.06		58.1	62.4
MOMBO2024.06		55.4	48.5
MOBILE2024.06		54	49.7
MOBILE2024.06		51.8	38.2
MOBILE2024.06		51.3	46
MOPO2024.06		42.1	41.4
MOPO2024.06		42.1	30.7
MOMBO2024.06		41	32.3
MOMBO2024.06		39.1	30.3
MOPO2024.06		33.8	33.6
MOPO2024.06		33.5	31.2
MOMBO2024.06		33.4	44.1
MOPO2024.06		29.5	32.9