List your company

Offline Reinforcement Learning on Minari 21 tasks

48.3Minari Adroit ScoreGFP actor
40.29242.37144.4546.529Dec 3, 2025

Evaluation results

MethodLinks
GFP actorAlgorithm=GFP, Policy Component=actor πθ2025.1248.391.7109.1124.574.1
GFP VaBCAlgorithm=GFP, Policy Component=VaBC πω2025.1246.191.5103.1122.271.6
FQLAlgorithm=FQL2025.1240.679.697.8121.765.9