List your company

Reinforcement Learning on Maze 5^4 structured discrete

9.74Mean ScoreDNC (SA), A2C
0.643.00255.3657.7275Feb 9, 2026

Evaluation results

MethodLinks
DNC (SA), A2CNum Seeds=102026.029.749.750.03014,507
DGRL (SDN, DBU)Num Seeds=102026.029.679.670.01014,390
DNC (greedy), A2CNum Seeds=102026.029.359.360.17-313,927
Wolpertinger, DBUNum Seeds=102026.028.318.631.13-1112,822
Wolpertinger, DDPGNum Seeds=102026.028.248.911.29-813,248
Cacla, A2CNum Seeds=102026.021.360.072.31-990
VAC, A2CNum Seeds=102026.020.990.980.64-891,374