List your company

Offline Reinforcement Learning on Adroit

137.7Adroit Mean ScorePBRL
0.10835.82971.55107.271Apr 4, 2025May 25, 2025Jul 16, 2025Sep 6, 2025Oct 27, 2025Dec 18, 2025Feb 8, 2026

Evaluation results

MethodLinks
PBRL2026.02137.7———————————————
OURS2026.02119.9———————————————
GPC-SAC2026.02118.8———————————————
IQL2026.02117.2———————————————
CQL2026.02107———————————————
Doctor2025.08100.2————————————85.74.99.6
MTM2025.0896.5————————————80.55.510.5
IQL2025.0888.3————————————83.33.21.8
DT2025.0875.1————————————65.227.9
BC2025.0856.6————————————56.10.50
PSSA2025.0448.6122105.2127.2108.475.70.20.2044.800.2-0.2———
TSSA2025.0447.9104.6105126.4106.389.70.40.4041.10.40.2-0.2———
FCNet2025.0441108102.9121.15057.70.41.2050.4-0.20.2-0.2———
CQL2025.0440.3107101.586.79537.59.94.40.239.20.42.1-0.1———
BC2025.0436.785.134.9125.6101.334.40.51.5056.9-0.10.8-0.1———
DT2025.0427.8110.495.589.715.3-0.20.10.30.222.70.10.3-0.3———
SpikeBert2025.0421.146.296.471.30.3200.20.3017.60.20.30———
SpikeGPT2025.0416.330.565.351.10.729.80.10.30.1170.20.30.1———
CQL2025.087.8————————————5.41.90.5
TD3+BC2025.085.4————————————5.10.10.2