Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.778Normalized Score
7
Feb 26, 2026
70.3Normalized Score
7
Feb 26, 2026
55.9Normalized Score
7
Feb 26, 2026
22.3Normalized Score
7
Feb 26, 2026
984Total Reward
7
Feb 26, 2026
965Total Reward
7
Feb 26, 2026
731Total Reward
7
Feb 26, 2026
955Total Reward
7
Feb 26, 2026
863Total Reward
7
Feb 26, 2026
947Total Reward
7
Feb 26, 2026
859Total Reward
7
Feb 26, 2026
739Total Reward
7
Feb 26, 2026
447Total Reward
7
Feb 26, 2026
982Total Reward
7
Feb 26, 2026
828Total Reward
7
Feb 26, 2026
856Total Reward
7
Feb 26, 2026
242Asterix Score
7
Feb 26, 2026
42.971Episode Reward
7
Feb 26, 2026
182.422Episode Reward
7
Feb 26, 2026
200Episode Reward
7
Feb 26, 2026
8,059Cumulative Return
7
Feb 26, 2026
5,168Return
7
May 15, 2026
1,515Return
7
Feb 26, 2026
1,269Return
7
Feb 26, 2026
412Return
7
Feb 26, 2026