Visual Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
960Episode Return
16
Feb 26, 2026
976Episode Return
16
Feb 26, 2026
802Episode Return
16
Feb 26, 2026
504Episode Return
16
Feb 26, 2026
969Episode Return
16
Feb 26, 2026
872Episode Return
16
Feb 26, 2026
9ER
15
Feb 26, 2026
619,221Environment Reward
11
Feb 26, 2026
871Walker Walk Score
10
Jul 2, 2026
884Average Return: Walker, Walk
10
Jul 2, 2026
2,408Assault Score
10
Mar 13, 2026
864Cartpole Swingup Score
8
Apr 28, 2026
408Quadruped Walk Score
6
Mar 13, 2026
-15Error Rate (ER)
6
Feb 26, 2026
-10ER
6
Feb 26, 2026
792Episode Reward (ER)
5
Feb 26, 2026
485Environment Reward
5
Feb 26, 2026
188ER
5
Feb 26, 2026