Continuous Control on Humanoid MuJoCo v2 (evaluation) benchmark leaderboard · SOTA2 Research

Continuous Control on Humanoid MuJoCo v2 (evaluation)

5,078.3Action Performance (p_act=0.1)DR-SPCRL

Updated 4mo ago

Evaluation Results

Method	Links
DR-SPCRL2025.11		5,078.3	3,334.7	1,648.8	831.5	542	298	276.4	290.8	337.2	334.2	259.3	243.5	251.1	239.6	239.9
SPACE2025.11		3,598.8	2,080.9	1,166	638.5	441.7	155.6	155	160.1	157.2	156.8	124.6	118.5	117.6	111.6	119
Linear2025.11		3,217.2	1,754.2	955.7	616.6	436.4	157.4	156.2	156.1	156.9	153.9	99.4	98.4	94.8	98	98.2
SAC2025.11		2,717.9	1,301.7	733.1	551.6	403.2	189.4	186.3	188.3	186.3	188.8	142.3	125.9	139.6	137.5	129.7
Dom. Rand.2025.11		2,608.7	1,349.7	765.5	537.9	384.4	123.4	122.3	121.2	117.7	121	109.3	103.2	105.4	105.2	105.7
Fixed2025.11		2,419.5	1,535.2	809.5	534	374.5	186.9	188.2	189.3	187.3	190.8	127.6	120.5	124.6	125.2	123.5
ACCEL2025.11		1,935	948.5	664.3	461.6	339.4	157.4	156.5	155.9	154	155.1	128.1	126.1	127.7	123.2	125.3
Self-Paced2025.11		1,740	1,250.9	776	533	357.3	271.5	303.8	281.4	280.6	261.7	275.7	254.5	198.1	219.7	217
Fixed2025.11		1,381.2	870.6	620.9	418.9	306	200.8	194.9	199	197.3	201.1	165.9	150.8	151.7	146.6	146.5
Linear2025.11		1,177.9	914.1	683.1	475.9	380.4	166.8	170	166.3	166.5	167.3	136.3	133	132.9	131	127.3
ACCEL2025.11		1,086.5	821.8	579.2	459.4	335.4	127.6	126.2	125.4	121.7	124.5	120.6	113	116.5	107.6	105.9
SPACE2025.11		976.3	818	639.9	483.7	379.9	233.3	233.2	237	238	238.1	121.4	126.1	113.4	119.8	123.4
DDPG2025.11		929.2	789.2	576.4	455.8	352.7	206	200	206.9	207.9	203.9	135.7	129.5	122.1	125.1	131.5
Dom. Rand.2025.11		912.9	731	567	424.9	358	124.6	124.1	124.3	123.2	125	107.5	102.6	103.3	101.8	107.8