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

Offline Reinforcement Learning on hopper Mixed Dataset

108Normalized RewardMOMBO

Evaluation Results

Method	Links
MOMBO2024.06		108	82.9
MOBILE2024.06		106.5	80.9
MOMBO2024.06		88.6	65.4
MOBILE2024.06		80.3	40.3
MOMBO2024.06		77.8	45.5
MOBILE2024.06		70.3	62.5
MOPO2024.06		67.2	34.1
MOMBO2024.06		60	50.1
MOMBO2024.06		58.4	60.1
MOMBO2024.06		51.5	32
MOPO2024.06		48.9	35.5
MOBILE2024.06		46.8	38.3
MOBILE2024.06		45	58.4
MOPO2024.06		43.6	29.2
MOBILE2024.06		43	42.1
MOPO2024.06		42.8	32.3
MOPO2024.06		37.3	33
MOPO2024.06		32	29.5
MOBILE2024.06		30.7	32.7
MOMBO2024.06		30.4	27.3
MOPO2024.06		24.7	22.5
MOBILE2024.06		22.9	21.8
MOPO2024.06		20	19.2
MOMBO2024.06		17.1	39.6