Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
775Episode Return
6
Mar 20, 2026
834Episode Return
6
Mar 20, 2026
925Episode Return
6
Mar 20, 2026
929Episode Return
6
Mar 20, 2026
939Episode Return
6
Mar 20, 2026
472Episode Return
6
Mar 20, 2026
479Episode Return
6
Mar 20, 2026
508Episode Return
6
Mar 20, 2026
842Episode Return
6
Mar 20, 2026
902Episode Return
6
Mar 20, 2026
884Episode Return
6
Mar 20, 2026
854Cumulative Reward
6
Mar 13, 2026
241Average Undiscounted Reward
6
Mar 13, 2026
80Avg Undiscounted Reward
6
Mar 13, 2026
500Cumulative Reward
6
Mar 13, 2026
3,389Alien Score
6
Mar 10, 2026
10.4Aggregated Return (All)
6
Mar 5, 2026
23.23Reward
6
Mar 4, 2026
2.51HNS
6
Feb 26, 2026
535HNS
6
Feb 26, 2026
98.2% Games Improved
6
Feb 27, 2026
0.51Reward
6
Feb 26, 2026
0.58Reward
6
Feb 26, 2026
0.72Reward
6
Feb 26, 2026
0.71Reward
6
Feb 26, 2026