Offline Goal-Conditioned Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
66Success Rate
14
May 21, 2026
96Success Rate
14
Apr 21, 2026
100Success Rate
13
May 22, 2026
81Success Rate
13
May 22, 2026
49Success Rate
13
May 22, 2026
32Success Rate
13
May 22, 2026
74Success Rate
13
May 22, 2026
9,100Success Rate
10
Feb 26, 2026
9,600Success Rate
10
Feb 26, 2026
9,500Success Rate
10
Feb 26, 2026
3,400Success Rate
10
Feb 26, 2026
92Success Rate
10
Feb 26, 2026
98Success Rate
10
Feb 26, 2026
11.5Discounted Return
10
Feb 26, 2026
2.73Discounted Return
10
Feb 26, 2026
18.2Discounted Return
10
Feb 26, 2026
19.7Discounted Return
10
Feb 26, 2026
30.1Discounted Return
10
Feb 26, 2026
99task1
9
Feb 26, 2026
99Task 1 Score
9
Feb 26, 2026
92Task 1 Score
9
Feb 26, 2026
98Task 1 Score
9
Feb 26, 2026
89Task 1 Score
9
Feb 26, 2026
49Task 1 Score
9
Feb 26, 2026
91Task 1 Score
9
Feb 26, 2026