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

Safe Reinforcement Learning on Safety-Gymnasium PointPush (OSRL)

0Cost

CPQ

-3.82421.98847.873.612Jun 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
0-12
2026.06
00.1
2026.06
01.5
2026.06
02.9
2026.06
0.8-2
2026.06
1.41.9
2026.06
2-1.2
2026.06
2.41.9
2026.06
2.50.7
2026.06
3.5-1.7
2026.06
3.9-23.6
2026.06
4.21.8
2026.06
5.81.2
2026.06
6-2.7
2026.06
6.41.4
2026.06
7.42.2
2026.06
7.51.2
2026.06
7.61.6
2026.06
8.20.3
2026.06
8.51.4
2026.06
8.62.2
2026.06
9.22.9
2026.06
9.62.6
2026.06
9.73.4
2026.06
9.83.8
2026.06
9.8-1
2026.06
10.30.4
2026.06
10.61.6
2026.06
11.4-1.5
2026.06
11.7-11.2
2026.06
11.8-18.2
2026.06
13.40.4
2026.06
14.42
2026.06
14.5-0.8
2026.06
27.83.2
2026.06
28.5-10.9
2026.06
28.7-0.1
2026.06
31.50.6
2026.06
31.51.6
2026.06
34.4-11.6
2026.06
35.74.3
2026.06
37.70.3
2026.06
38.9-6.9
2026.06
40.53.6
2026.06
45.32.2
2026.06
53-0.4
2026.06
82.83.7
2026.06
95.6-3.4