Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
56.68Performance
20
May 19, 2026
0.809Median HNS
20
Feb 26, 2026
684,700Score
20
Apr 6, 2026
223Median Human-Normalized Score
20
Feb 26, 2026
8.59Sample Time (s)
19
Jun 23, 2026
21Mean Episode Return
19
Apr 6, 2026
17,313Score
19
Feb 26, 2026
6,712Score
19
Feb 26, 2026
6.2Normalized Mean Return
18
May 15, 2026
9.41Normalized Mean Return
18
May 15, 2026
1.1Normalized Mean Return
18
May 15, 2026
271Normalized Performance
18
Feb 26, 2026
10,490Average Return
18
Feb 26, 2026
10,133Average Return
18
Feb 26, 2026
8,004Average Return
18
Feb 26, 2026
4,408Average Return
18
Feb 26, 2026
18,165Average Return
18
Feb 26, 2026
9,359.92Avg Episode Reward
18
May 12, 2026
7,282Mean Episodic Return
17
Mar 4, 2026
5,222Mean Episodic Return
17
Mar 4, 2026
3,268Mean Episodic Return
17
Mar 4, 2026
5,953Mean Episodic Return
17
Mar 4, 2026
14,845Mean Episodic Return
17
Mar 4, 2026
3,455Total Return
17
Mar 16, 2026
4,966Cumulative Return
17
Mar 16, 2026