Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
-145.6Cumulative Return
10
Feb 26, 2026
280.9Return
10
Feb 26, 2026
-82.5Average Returns
10
May 11, 2026
20.51Max Reward
10
Feb 26, 2026
30Average Return
10
Feb 26, 2026
11.6Mean Return
10
Feb 26, 2026
1,473Mean Score
10
Mar 4, 2026
1,160Mean Human-Normalized Score
10
Feb 26, 2026
6Worst Rank
10
Feb 26, 2026
892.9Avg Episode Reward
10
Feb 26, 2026
-101.72Total Reward
10
Feb 26, 2026
124,524.02Alien Score
10
Feb 26, 2026
7,459Average Reward (0.3/1.7)
10
Feb 26, 2026
200Average Reward (EpLen=2, DF=0.5)
10
Feb 26, 2026
7,459Average Reward (0.3/1.7)
10
Feb 26, 2026
-45Avg Reward (gamma=0.01)
10
Feb 26, 2026
7,459Average Reward (0.3/1.7)
10
Feb 26, 2026
3,351.4GRAVITAR Score
10
Feb 26, 2026
4,704Alien Score
10
Feb 26, 2026
6,875Alien
10
Feb 26, 2026
94Task 1 Performance
9
May 22, 2026
9.55Grand Average Return (G)
9
May 22, 2026
18.01Grand Average Return
9
May 22, 2026
32.29Grand Average Return
9
May 22, 2026
54.31Grand Average Return (G)
9
May 22, 2026