List your company

Cross-domain Offline Reinforcement Learning on MuJoCo HalfCheetah

73.8Normalized ScoreV2A
11.9227.98544.0560.115May 24, 2026

Evaluation results

MethodLinks
V2ABase Alignment=OTDF, Source=half-me, Target=e2026.0573.8—————————
V2ABase Alignment=IGDF, Source=half-me, Target=e2026.0562.7—————————
V2ABase Alignment=IGDF, Source=half-me, Target=m2026.0560.7—————————
V2ABase Alignment=OTDF, Source=half-mr, Target=me2026.0557.3—————————
V2ABase Alignment=IGDF, Source=half-me, Target=me2026.0551.7—————————
V2ABase Alignment=IGDF, Source=half-mr, Target=me2026.0551.4—————————
V2ABase Alignment=OTDF, Source=half-me, Target=me2026.0549.5—————————
V2ABase Alignment=OTDF, Source=half-me, Target=m2026.0549.4—————————
V2ABase Alignment=OTDF, Source=half-mr, Target=m2026.0535.6—————————
V2ABase Alignment=OTDF, Source=half-mr, Target=e2026.0530.7—————————
DVDFBase Alignment=IGDF, Source=half-mr, Target=m2026.0528.3—————————
IQLSource=half-mr, Target=m2026.0527.9—————————
OTDFSource=half-mr, Target=m2026.0527.3—————————
V2ABase Alignment=IGDF, Source=half-mr, Target=m2026.0526.8—————————
V2ABase Alignment=IGDF, Source=half-mr, Target=e2026.0526.4—————————
DVDFBase Alignment=OTDF, Source=half-mr, Target=m2026.0524.9—————————
IGDFSource=half-mr, Target=m2026.0524.6—————————
DARASource=half-mr, Target=m2026.0520.2—————————
BOSASource=half-mr, Target=m2026.0514.3—————————
BOSA2026.05—8.38.710.87.56.610.4306.84.9
DARA2026.05—10.612.912.111.59.214.825.99.510.4
IGDF2026.05—23.69.812.811.68.613.921.98.910.7
IQL*2026.05—12.310.812.6106.513.621.87.69.1
OTDF2026.05—40.210.18.737.89.77.230.710.93.2
SRPO2026.05—16.810.312.210.29.514.817.29.611.2
TCE(OG)2026.05—42.240.721.34241.623.441.94011.2
TCE(SM)2026.05—41.640.16.741.737.84.341.739.84.3