Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
General Reinforcement Learning Objectives on Didactic Environment
Loading...
99
Linear Performance
FB flow
94.84
95.92
97
98.08
Feb 6, 2026
Linear Performance
Goal Reaching Success Rate
Imitation Learning (Deterministic)
Imitation Learning (Stochastic)
Exploration Score
Constrained RL Success Rate
Robustness Score
Average Performance
Updated 4d ago
Evaluation Results
Method
Method
Links
Linear Performance
Goal Reaching Success Rate
Imitation Learning (Deterministic)
Imitation Learning (Stochastic)
Exploration Score
Constrained RL Success Rate
Robustness Score
Average Performance
FB flow
Protocol=Zero-shot, Me...
2026.02
99
100
86
77
37
0
79
68
SFB flow
Protocol=Zero-shot, Me...
2026.02
99
100
90
83
90
65
96
89
FB
Protocol=Zero-shot, Me...
2026.02
96
100
78
67
37
0
1
54
SFB
Protocol=Zero-shot, Me...
2026.02
95
100
78
79
49
0
39
63
Feedback
Search any
task
Search any
task
