Offline Reinforcement Learning on D4RL Gym Locomotion v2 benchmark leaderboard · SOTA2 Research

Offline Reinforcement Learning on D4RL Gym Locomotion v2

54.9HalfCheetah (Medium)DMG

Evaluation Results

Method	Links
DMG2024.11		54.9	100.6	92.4	51.4	101.9	89.7	91.1	110.4	114.4	95.9	111.5	114.7	28.8	20.4	4.8	1,182.8
OneStep2024.11		50.4	87.5	84.8	42.7	98.5	61.7	75.1	108.6	111.3	88.2	106.9	110.7	2.3	5.6	6.9	1,041.2
BiTrajDiff2025.06		50.3	79	86.7	45	85	89.9	96.3	109	110.2	—	—	—	—	—	—	83.5
DiffStitch2025.06		50.1	67.9	85.5	45.1	71.5	80.5	95.9	97.5	109.6	—	—	—	—	—	—	78.2
Synther2025.06		49.7	61.2	83.4	44.5	76.4	81.1	95.5	106.2	109.4	—	—	—	—	—	—	78.6
RTDiff2025.06		49.4	62.6	85.4	44	72.1	83.5	93.9	106.8	109.6	—	—	—	—	—	—	78.6
Synther2025.06		49.2	61.1	85.8	46.2	100.6	86.7	86.6	111.2	112.1	—	—	—	—	—	—	82.2
RTDiff2025.06		48.9	62	82.7	43.7	97.7	74	92	110.5	111.9	—	—	—	—	—	—	80.4
DiffStitch2025.06		48.6	65.5	79.8	43.6	96.4	74.9	90.3	108.6	111.2	—	—	—	—	—	—	79.9
BiTrajDiff2025.06		48.6	81.1	86.7	44.1	102.8	87.6	95.3	110.9	112.5	—	—	—	—	—	—	85.5
TD3BC2025.06		48.4	60.4	82	44.1	64.4	80.9	92.3	94.2	109.3	—	—	—	—	—	—	75.1
TD3BC2024.11		48.3	59.3	83.7	44.6	60.9	81.8	90.7	98	110.1	96.7	107.8	110.2	11	8.5	1.6	1,013.2
IQL2025.06		48.2	67	77.6	43.5	94.7	73.3	90.1	105.4	112.4	—	—	—	—	—	—	79.1
AWAC2024.11		47.9	59.8	83.1	44.8	69.8	78.1	64.9	100.1	110	81.7	109.5	110.1	6.1	9.2	0.2	975.3
IQL2024.11		47.4	66.2	78.3	44.2	94.7	73.8	86.7	91.5	109.6	95	109.4	109.9	13.1	7.9	5.4	1,033.1
CQL2024.11		47	53	73.3	45.5	88.7	81.8	75.6	105.6	107.9	96.3	96.5	108.5	17.5	7.9	5.1	1,010.2
BCQ2024.11		46.6	59.4	71.8	42.2	60.9	57	95.4	106.9	107.7	89.9	109	106.3	2.2	7.8	4.9	968
BEAR2024.11		43	51.8	-0.2	36.3	52.2	7	46	50.6	22.1	92.7	54.6	106.6	2.3	3.9	12.8	581.7
DT2024.11		42.6	67.6	74	36.6	82.7	66.6	86.8	107.6	108.1	87.7	94.2	108.3	2.2	5.4	2.2	972.6
BC2024.11		42	56.2	71	36.4	21.8	24.9	59.6	51.7	101.2	92.9	110.9	107.7	2.6	4.1	1.2	784.2