Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
155.8------135.6128.4139.9--
2025.10
140.6------152186.8159.8--
2025.10
138.3------154.5206.1166.3--
2025.10
136.6------150.7203.6163.6--
2026.03
130.59------88.61204.76141.32-423.96
2025.10
113.9------121.5123119.5--
2026.03
106.87------105.1178.3396.77-290.31
2026.01
100.6---125.5108.7155.915697.3111.435.7-
2026.03
95.26------57.0495.682.64-247.9
2026.01
87.8---130.3145.9166.1122.3152.9126.983-
2026.01
76.9---117.685.7133.593.282.289.437-
2026.01
76.9---138119.9160118140115.757-
2025.10
73.9------73.874.474--
2026.01
72.5---63.4119.4115.496.458.383.358-
2026.01
68.6---103.6100.1181.7104.4103.2103.663.6-
2026.03
65.65------84.63215.5121.92-365.78
2026.03
59.03------117.6190.1688.93-266.8
2026.01
58.9---51.481.2217.2132228.1120.675.4-
2025.10
57.9------89.590.179.2--
2026.01
52.8---115.1100.9149.3127.7126.5106.170.1-
2024.05
50.19------49.625.4941.76--
2026.03
42.11------34.8561.7246.23-138.68
2024.05
39.43------55.2418.4937.72--
2024.05
39.38------55.0518.6937.71--
2026.01
35.9---74.13878.580.142.757.452.3-
2026.03
29.41------59.4597.161.99-185.96
2026.03
18.08------31.7135.6628.48-85.45
2026.01
17.9---86.568.8105.8107.3115.474.822.1-
2026.01
13.5---104.520.891.976.628.549.712.3-
2025.10
3.8------30.3513--
2026.03
-8.9------86.1123.7533.65-100.96
2021.10
--3.2-0.5-1.7-6.92.7-0.3-----
2021.10
-139.582.483.198.3102.6124-----
2021.10
-65.7-81--133-----
2021.10
--70.6---------
2021.10
----51.5-------
2021.10
-----41.7------
2021.10
-76.468.514.1-84.2------
2021.10
----94.3-------
2021.10
------36.8-----