List your company

Offline Reinforcement Learning on Maze2D medium v1

166.82Normalized ReturnInverter
-5.851238.976983.805128.6331Dec 8, 2025Jan 4, 2026Feb 1, 2026Feb 28, 2026Mar 28, 2026Apr 24, 2026May 22, 2026

Evaluation results

MethodLinks
InverterK=16, #NN-passes=38, ms/NN-pass=1.62 ms, other=11.2 ms, sum=72.9ms, × slower=1.0×2026.05166.821.2
Diffuser#NN-passes=256, ms/NN-pass=14.54 ms, other=14.5 ms, sum=3.74s, × slower=51.3×2026.05130.0722.7
ReBRAC#NN-passes=600, ms/NN-pass=0.21 ms†, sum=126.0ms†, × slower=1.7×2026.05105.1131.67
SAC-N#NN-passes=600, ms/NN-pass=1.80 ms, sum=1.08s, × slower=14.8×2026.0588.6118.72
CQL#NN-passes=600, ms/NN-pass=1.84 ms, sum=1.10s, × slower=15.1×2026.0586.119.68
TD3+BC#NN-passes=600, ms/NN-pass=1.67 ms, sum=1.00s, × slower=13.8×2026.0559.4536.25
EDAC#NN-passes=600, ms/NN-pass=1.74 ms, sum=1.04s, × slower=14.3×2026.0557.043.45
AWAC#NN-passes=600, ms/NN-pass=1.28 ms, sum=765.0ms, × slower=10.5×2026.0552.8855.12
PrivORL-jRL Algorithm=IQL, epsilon=102025.1249.3—
PrivORL-jRL Algorithm=TD3PLUSBC, epsilon=102025.1238—
PrivORL-jRL Algorithm=EDAC, epsilon=102025.1235—
IQL#NN-passes=600, ms/NN-pass=1.69 ms, sum=1.02s, × slower=14.0×2026.0534.852.72
DP-TransformerRL Algorithm=IQL, epsilon=102025.1232.8—
DT#NN-passes=600, ms/NN-pass=3.57 ms, sum=2.14s, × slower=29.4×2026.0531.7126.33
PrivORL-jRL Algorithm=EDAC, epsilon=12025.1231.5—
PrivORL-jRL Algorithm=TD3PLUSBC, epsilon=12025.1231.1—
DP-TransformerRL Algorithm=TD3PLUSBC, epsilon=102025.1226.6—
PrivORL-jRL Algorithm=IQL, epsilon=12025.1223.4—
DP-TransformerRL Algorithm=EDAC, epsilon=102025.1219—
DP-TransformerRL Algorithm=IQL, epsilon=12025.1218.1—
PrivORL-j-URL Algorithm=EDAC, epsilon=102025.1216.4—
BC-10%#NN-passes=600, ms/NN-pass=1.25 ms, sum=749.8ms, × slower=10.3×2026.0514.252.33
PrivORL-j-URL Algorithm=IQL, epsilon=102025.1214.1—
PrivORL-j-URL Algorithm=EDAC, epsilon=12025.1213.5—
PrivORL-j-URL Algorithm=TD3PLUSBC, epsilon=102025.1210.8—
DP-TransformerRL Algorithm=EDAC, epsilon=12025.1210.2—
DP-TransformerRL Algorithm=TD3PLUSBC, epsilon=12025.127.6—
PrivORL-j-URL Algorithm=TD3PLUSBC, epsilon=12025.126.7—
PrivORL-j-URL Algorithm=IQL, epsilon=12025.125.5—
BC#NN-passes=600, ms/NN-pass=1.70 ms, sum=1.02s, × slower=14.0×2026.050.793.25