Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
306.79Average Reward
5
Feb 26, 2026
173.97Average Reward
5
Feb 26, 2026
110.74Average Reward
5
Feb 26, 2026
226.72Average Reward
5
Feb 26, 2026
160.88Average Reward
5
Feb 26, 2026
863Quadruped-Run
5
Feb 26, 2026
529Cheetah-Run Score
5
Feb 26, 2026
89.4Final Score (1M Online Steps)
5
Feb 26, 2026
97.4Final Score (1M Online Steps)
5
Feb 26, 2026
99.2Final Score
5
Feb 26, 2026
124,524.02Alien Score
5
Feb 26, 2026
100Mean CHNS
5
Feb 26, 2026
16,218Alien Score
5
Feb 26, 2026
731.1Median Human-Normalized Score
5
Feb 26, 2026
448Median Human-Normalized Score
5
Feb 26, 2026
1,859Final Mean Performance
5
Feb 26, 2026
12,380Final Mean Performance
5
Feb 26, 2026
69,571Final Mean Performance
5
Feb 26, 2026
6,464Final Mean Performance
5
Feb 26, 2026
6,072Beam Rider Score
5
Feb 26, 2026
5,501.5Game Score
5
Feb 26, 2026
0Score
5
Feb 26, 2026
3,690Average Total Reward
5
Feb 26, 2026
28,010Avg Total Reward
5
Feb 26, 2026
18,900Average Total Reward
5
Feb 26, 2026