List your company

Offline Reinforcement Learning on D4RL Maze2D

155.8Return (UMaze)HD
-15.48828.98173.45117.919May 27, 2024Sep 15, 2024Jan 4, 2025Apr 25, 2025Aug 14, 2025Dec 3, 2025Mar 24, 2026

Evaluation results

MethodLinks
HD2025.10155.8——————135.6128.4139.9——
DQL*2025.10140.6——————152186.8159.8——
MDD2025.10138.3——————154.5206.1166.3——
DV2025.10136.6——————150.7203.6163.6——
SAC-N2026.03130.59——————88.61204.76141.32—423.96
Diffuser2025.10113.9——————121.5123119.5——
ReBRAC2026.03106.87——————105.1178.3396.77—290.31
A2PRdataset_size=10k samples2026.01100.6———125.5108.7155.915697.3111.435.7—
EDAC2026.0395.26——————57.0495.682.64—247.9
C4dataset_size=10k samples2026.0187.8———130.3145.9166.1122.3152.9126.983—
DR3dataset_size=10k samples2026.0176.9———117.685.7133.593.282.289.437—
TSRLdataset_size=10k samples2026.0176.9———138119.9160118140115.757—
SfBC2025.1073.9——————73.874.474——
SORLdataset_size=10k samples2026.0172.5———63.4119.4115.496.458.383.358—
IQLdataset_size=10k samples2026.0168.6———103.6100.1181.7104.4103.2103.663.6—
AWAC2026.0365.65——————84.63215.5121.92—365.78
GEM2026.0359.03——————117.6190.1688.93—266.8
BPPOdataset_size=10k samples2026.0158.9———51.481.2217.2132228.1120.675.4—
IDQL2025.1057.9——————89.590.179.2——
DOGEdataset_size=10k samples2026.0152.8———115.1100.9149.3127.7126.5106.170.1—
Decision TransformerAugmentation=GTA, Number of evaluations=100, Number of seeds=42024.0550.19——————49.625.4941.76——
IQL2026.0342.11——————34.8561.7246.23—138.68
Decision TransformerAugmentation=None, Number of evaluations=100, Number of seeds=42024.0539.43——————55.2418.4937.72——
Decision TransformerAugmentation=S4RL, Number of evaluations=100, Number of seeds=42024.0539.38——————55.0518.6937.71——
CQLdataset_size=10k samples2026.0135.9———74.13878.580.142.757.452.3—
TD3+BC2026.0329.41——————59.4597.161.99—185.96
DT2026.0318.08——————31.7135.6628.48—85.45
LNdataset_size=10k samples2026.0117.9———86.568.8105.8107.3115.474.822.1—
TD3BCdataset_size=10k samples2026.0113.5———104.520.891.976.628.549.712.3—
BC2025.103.8——————30.3513——
CQL2026.03-8.9——————86.1123.7533.65—100.96
BAILCategory=Model-Free2021.10—————41.7——————
BCCategory=Baseline2021.10—-3.2-0.5-1.7-6.92.7-0.3—————
BEARCategory=Model-Free2021.10—65.7—81——133—————
BRAC-PCategory=Model-Free2021.10————51.5———————
BRAC-vCategory=Model-Free2021.10——70.6—————————
COMBOCategory=Model-Based2021.10—76.468.514.1—84.2——————
MOPOCategory=Model-Based2021.10——————36.8—————
Repb-SDECategory=Model-Based2021.10————94.3———————
ROMI-BCQCategory=Proposed2021.10—139.582.483.198.3102.6124—————