General Reinforcement Learning Objectives on Didactic Environment
99Linear PerformanceFB flow
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| FB flowProtocol=Zero-shot, Method Variant=Flow-based measure2026.02 | 99 | 100 | 86 | 77 | 37 | 0 | 79 | 68 | |
| SFB flowProtocol=Zero-shot, Method Variant=Flow-based measure2026.02 | 99 | 100 | 90 | 83 | 90 | 65 | 96 | 89 | |
| FBProtocol=Zero-shot, Method Variant=Explicit measure2026.02 | 96 | 100 | 78 | 67 | 37 | 0 | 1 | 54 | |
| SFBProtocol=Zero-shot, Method Variant=Explicit measure2026.02 | 95 | 100 | 78 | 79 | 49 | 0 | 39 | 63 |