List your company

Reinforcement Learning on Maze 17^10 structured discrete

9.61Mean ScoreDGRL (SDN, DBU)
0.81163.09585.387.6642Feb 9, 2026

Evaluation results

MethodLinks
DGRL (SDN, DBU)Num Seeds=102026.029.619.630.04019,548
SDN (EU), DBUNum Seeds=102026.029.579.60.08019,494
SDN (MH), DBUNum Seeds=102026.029.569.610.14019,505
DNC (SA), DBUNum Seeds=102026.029.169.220.16-418,730
DNC (SA), A2CNum Seeds=102026.028.799.691.33019,668
SDN, A2CNum Seeds=102026.028.658.730.42-917,740
SDN, DDPGNum Seeds=102026.027.888.792.33-917,863
DNC (greedy), A2CNum Seeds=102026.026.757.282.72-2414,804
Cacla, A2CNum Seeds=102026.021.15-0.052.01-1000