List your company

Reinforcement Learning on MiniGrid (Training Duration)

5.82Training Duration (hours)DR
4.249614.849825.4536.0502Jun 24, 2025

Evaluation results

MethodLinks
DRNumber of updates=10k2025.065.82
DRNumber of updates=20k2025.0612.41
ACCELNumber of updates=10k2025.0612.94
TRACEDNumber of updates=10k2025.0613.78
PLR⊥Number of updates=10k2025.0614.87
ADDNumber of updates=10k2025.0622.48
ACCELNumber of updates=20k2025.0626.58
PLR⊥Number of updates=20k2025.0631.83
ADDNumber of updates=20k2025.0645.08