List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on AntMaze Medium-Diverse v2

6.6Average ScoreTRACER
-0.2641.5183.35.082Nov 1, 2024Feb 3, 2025May 9, 2025Aug 11, 2025Nov 14, 2025Feb 16, 2026May 22, 2026
Updated 5mo ago

Evaluation results

MethodLinks
TRACERcorruption_type=random simultaneous corruptions2024.116.6
Inverterx slower per env step=1.0x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050.965
ReBRACx slower per env step=1.6x†, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=JAX+JIT2026.050.835
IQLx slower per env step=12.9x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050.738
CQLx slower per env step=14.0x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050.672
BC-10%x slower per env step=9.5x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050.058
BCx slower per env step=13.0x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050.008
TD3+BCx slower per env step=12.7x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050.002
IQLcorruption_type=random simultaneous corruptions2024.110
RIQLcorruption_type=random simultaneous corruptions2024.110
AWACx slower per env step=9.8x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050
SAC-Nx slower per env step=13.7x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050
EDACx slower per env step=13.3x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050
DTx slower per env step=27.3x, Hardware=single A40 GPU, Batch size=1, Number of episodes=100, Implementation framework=PyTorch2026.050